Txt: Some students came to school by car.
Hyp: Some students did come to school . (yes)
Some DT |
students NNS |
did VBD |
come VBN |
school NN |
. . |
|
Some:DT | 0.00 | 20.00 | 20.00 | 15.00 | 20.00 | 10.00 |
students:NNS | 20.00 | 0.00 | 14.74 | 15.00 | 0.75 | 20.00 |
came:VBD | 20.00 | 15.00 | 4.19 | 0.50 | 12.45 | 17.90 |
school:NN | 20.00 | 0.75 | 10.44 | 12.45 | 0.00 | 19.99 |
car:NN | 20.00 | 8.95 | 12.91 | 14.56 | 7.06 | 19.69 |
.:. | 10.00 | 20.00 | 17.99 | 18.30 | 19.99 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -1.5000
Features matched: Adjunct.dropPosCxt: text adjunct "car" of "came" dropped on aligned hyp word "come"; NullPunisher.aux: did; Quant.contract: [some,some]; Adjunct.dropPosCxt&Align.veryGood:
Hand-tuned score: 2.9500
Threshold: -11.4590
Txt: No students came to school by car.
Hyp: Some students did come to school . (unknown)
Some DT |
students NNS |
did VBD |
come VBN |
school NN |
. . |
|
No:DT | 10.00 | 20.00 | 20.00 | 20.00 | 20.00 | 10.00 |
students:NNS | 20.00 | 0.00 | 14.74 | 15.00 | 0.75 | 20.00 |
came:VBD | 20.00 | 15.00 | 4.19 | 0.50 | 12.45 | 17.90 |
school:NN | 20.00 | 0.75 | 10.44 | 12.45 | 0.00 | 19.99 |
car:NN | 20.00 | 8.95 | 12.91 | 14.56 | 7.06 | 19.69 |
.:. | 10.00 | 20.00 | 17.99 | 18.30 | 19.99 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: dontknow (INCORRECT)
Justification:
Alignment score: -11.5000
Features matched: Adjunct.dropPosCxt: text adjunct "car" of "came" dropped on aligned hyp word "come"; Antonym.samePol: matching polarity with antonyms: Some & No; NullPunisher.aux: did; Quant.oneNo: [no,some[
Hand-tuned score: -12.5500
Threshold: -11.4590
Txt: Ed drove legally.
Hyp: Ed did drive . (yes)
Ed NNP |
did VBD |
drive NN |
. . |
|
Ed:NNP | 0.00 | 15.00 | 3.90 | 20.00 |
drove:VBD | 15.00 | 8.93 | 0.50 | 18.77 |
legally:RB | 14.96 | 17.86 | 14.50 | 19.03 |
.:. | 20.00 | 17.99 | 19.58 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -11.4320
Features matched: Adjunct.dropPosCxt: text adjunct "legally" of "drove" dropped on aligned hyp word "drive"; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "drove"
Hand-tuned score: -0.5000
Threshold: -11.4590
Txt: Ed drove predictably.
Hyp: Ed did drive . (yes)
Ed NNP |
did VBD |
drive NN |
. . |
|
Ed:NNP | 0.00 | 15.00 | 3.90 | 20.00 |
drove:VBD | 15.00 | 8.93 | 0.50 | 18.77 |
predictably:RB | 14.96 | 19.17 | 14.68 | 20.00 |
.:. | 20.00 | 17.99 | 19.58 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -11.4320
Features matched: Adjunct.dropPosCxt: text adjunct "predictably" of "drove" dropped on aligned hyp word "drive"; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "drove"
Hand-tuned score: -0.5000
Threshold: -11.4590
Txt: Legally, Ed could drive.
Hyp: Ed did drive . (unknown)
Ed NNP |
did VBD |
drive NN |
. . |
|
Legally:RB | 14.96 | 19.96 | 14.96 | 20.00 |
,:, | 20.00 | 19.80 | 19.25 | 5.73 |
Ed:NNP | 0.00 | 15.00 | 3.90 | 20.00 |
could:MD | 19.96 | 17.84 | 19.96 | 10.00 |
drive:VB | 8.90 | 6.26 | 0.00 | 19.58 |
.:. | 20.00 | 17.99 | 19.58 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -8.2597
Features matched: Adjunct.dropPosCxt: text adjunct "Legally" of "drive" dropped on aligned hyp word "drive"; Modal.dontKnow: possible -> actual; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "drive"
Hand-tuned score: -2.5000
Threshold: -11.4590
Txt: Predictably, Ed drove.
Hyp: Ed did drive . (yes)
Ed NNP |
did VBD |
drive NN |
. . |
|
Predictably:RB | 14.96 | 19.96 | 14.96 | 20.00 |
,:, | 20.00 | 19.80 | 19.25 | 5.73 |
Ed:NNP | 0.00 | 15.00 | 3.90 | 20.00 |
drove:VBD | 15.00 | 8.93 | 0.50 | 18.77 |
.:. | 20.00 | 17.99 | 19.58 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -11.4320
Features matched: Adjunct.dropPosCxt: text adjunct "Predictably" of "drove" dropped on aligned hyp word "drive"; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "drove"
Hand-tuned score: -0.5000
Threshold: -11.4590
Txt: The technician cooled the room.
Hyp: The technician did lower the temperature of the room . (yes)
The DT |
technician NN |
did VBD |
lower JJR |
the DT |
temperature NN |
the DT |
room NN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 0.00 | 20.00 | 10.00 |
technician:NN | 20.00 | 0.00 | 12.84 | 10.95 | 20.00 | 8.15 | 20.00 | 8.71 | 20.00 |
cooled:VBD | 20.00 | 13.08 | 7.53 | 9.62 | 20.00 | 9.59 | 20.00 | 13.15 | 19.82 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 0.00 | 20.00 | 10.00 |
room:NN | 20.00 | 8.71 | 13.03 | 8.31 | 20.00 | 6.97 | 20.00 | 0.00 | 19.15 |
.:. | 10.00 | 20.00 | 17.99 | 19.18 | 10.00 | 20.00 | 10.00 | 19.15 | 0.00 |
NO_WORD | 1.00 | 10.00 | 10.00 | 9.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -25.4975
Features matched: Adjunct.addPosCxt: hyp added lower[lower-JJR]; NullPunisher.other: lower; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "cooled"
Hand-tuned score: -3.0000
Threshold: -11.4590
Txt: The technician raised the temperature of the room.
Hyp: The technician did cool the room . (no)
The DT |
technician NN |
did VBD |
cool VB |
the DT |
room NN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
technician:NN | 20.00 | 0.00 | 12.84 | 13.08 | 20.00 | 8.71 | 20.00 |
raised:VBD | 20.00 | 13.95 | 5.44 | 6.95 | 20.00 | 13.69 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
temperature:NN | 20.00 | 8.15 | 12.53 | 9.59 | 20.00 | 6.97 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
room:NN | 20.00 | 8.71 | 13.03 | 11.00 | 20.00 | 0.00 | 19.15 |
.:. | 10.00 | 20.00 | 17.99 | 20.00 | 10.00 | 19.15 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -9.9537
Features matched: NullPunisher.aux: did; RootEntailment.poorlyAlignedRoot: "cool" aligned badly to "raised"; Structure.parentsMismatch: args have different parents, different relations: text "room" <-prep_of-- "temperature" vs. hyp "room" <-dobj-- "cool", which aligned to text "raised"
Hand-tuned score: -4.0500
Threshold: -11.4590
Txt: The president visited Iraq in September.
Hyp: The president has gone to Iraq . (yes)
The DT |
president NN |
has VBZ |
gone VBN |
Iraq NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
president:NN | 20.00 | 0.00 | 14.34 | 12.72 | 9.84 | 20.00 |
visited:VBD | 20.00 | 13.07 | 10.00 | 7.43 | 15.50 | 19.78 |
Iraq:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
September:NNP | 20.50 | 10.50 | 14.19 | 12.73 | 15.00 | 20.50 |
.:. | 10.00 | 20.00 | 20.00 | 19.35 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -10.4338
Features matched: Adjunct.dropPosCxt: text adjunct "September" of "Iraq" dropped on aligned hyp word "Iraq"; NullPunisher.aux: has; RootEntailment.poorlyAlignedRoot: "gone" aligned badly to "visited"; Structure.relMismatch: text "Iraq" is dobj of "visited" while hyp "Iraq" is prep_to of "gone" which aligned to text "visited"
Hand-tuned score: -1.5500
Threshold: -11.4590
Txt: Jones has visited Iraq.
Hyp: Jones did visit Iraq in September . (unknown)
Jones NNP |
did VBD |
visit VB |
Iraq NNP |
September NNP |
. . |
|
Jones:NNP | 0.00 | 15.50 | 15.50 | 14.34 | 15.00 | 20.50 |
has:VBZ | 14.84 | 7.53 | 10.00 | 13.02 | 14.19 | 20.00 |
visited:VBN | 15.50 | 7.62 | 0.31 | 15.50 | 15.50 | 19.78 |
Iraq:NNP | 14.34 | 15.50 | 15.50 | 0.00 | 15.00 | 20.50 |
.:. | 20.50 | 17.99 | 20.00 | 20.50 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -11.3094
Features matched: Adjunct.addPosCxt: hyp added September[September-NNP]; Date.hypDateIns: hypothesis date insertion: September; NullPunisher.aux: did; NullPunisher.other: September
Hand-tuned score: -3.0500
Threshold: -11.4590
Txt: Jones arrived in Paris in September last year.
Hyp: Jones did arrive in Paris last year . (yes)
Jones NNP |
did VBD |
arrive VB |
Paris NNP |
last JJ |
year NN |
. . |
|
Jones:NNP | 0.50 | 15.00 | 15.00 | 9.84 | 11.45 | 10.50 | 20.00 |
arrived:VBD | 15.50 | 7.47 | 0.50 | 15.50 | 12.50 | 15.28 | 20.00 |
Paris:NNP | 14.34 | 15.50 | 15.50 | 0.00 | 16.34 | 13.13 | 20.50 |
September:NNP | 15.00 | 14.19 | 15.50 | 15.00 | 9.84 | 7.23 | 20.50 |
last:JJ | 15.95 | 10.19 | 12.50 | 16.34 | 0.00 | 9.84 | 20.50 |
year:NN | 15.00 | 14.19 | 15.50 | 13.13 | 9.84 | 0.00 | 17.60 |
.:. | 20.50 | 17.99 | 20.00 | 20.50 | 20.50 | 17.60 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.0000
Features matched: Adjunct.dropPosCxt: text adjunct "September" of "Paris" dropped on aligned hyp word "Paris"; Date.matchDatesByGraph: hyp/txt matching, by graph: year and children; NullPunisher.aux: did
Hand-tuned score: 2.4500
Threshold: -11.4590
Txt: Jones arrived in Paris in September last year.
Hyp: Jones did arrive in Paris in September . (unknown)
Jones NNP |
did VBD |
arrive VB |
Paris NNP |
September NNP |
. . |
|
Jones:NNP | 0.50 | 15.00 | 15.00 | 9.84 | 10.50 | 20.00 |
arrived:VBD | 15.50 | 7.47 | 0.50 | 15.50 | 15.50 | 20.00 |
Paris:NNP | 14.34 | 15.50 | 15.50 | 0.00 | 15.00 | 20.50 |
September:NNP | 15.00 | 14.19 | 15.50 | 15.00 | 0.00 | 20.50 |
last:JJ | 15.95 | 10.19 | 12.50 | 16.34 | 9.84 | 20.50 |
year:NN | 15.00 | 14.19 | 15.50 | 13.13 | 7.23 | 17.60 |
.:. | 20.50 | 17.99 | 20.00 | 20.50 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.0000
Features matched: Adjunct.dropPosCxt: text adjunct "year" of "arrived" dropped on aligned hyp word "arrive"; Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 09/01/1000; NullPunisher.aux: did
Hand-tuned score: 2.4500
Threshold: -11.4590
Txt: Jones arrived on a Sunday in September.
Hyp: Jones did arrive on a Sunday . (yes)
Jones NNP |
did VBD |
arrive VB |
a DT |
Sunday NNP |
. . |
|
Jones:NNP | 0.50 | 15.00 | 15.00 | 20.00 | 10.50 | 20.00 |
arrived:VBD | 15.50 | 7.47 | 0.50 | 20.00 | 15.50 | 20.00 |
a:DT | 20.50 | 20.00 | 20.00 | 0.00 | 20.50 | 10.00 |
Sunday:NNP | 15.00 | 10.20 | 15.50 | 20.50 | 0.00 | 20.50 |
September:NNP | 15.00 | 14.19 | 15.50 | 20.50 | 7.23 | 20.50 |
.:. | 20.50 | 17.99 | 20.00 | 10.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.0000
Features matched: Adjunct.dropPosCxt: text adjunct "September" of "arrived" dropped on aligned hyp word "arrive"; Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/1000; NullPunisher.aux: did; Quant.contract: [a,a]
Hand-tuned score: 3.4500
Threshold: -11.4590
Txt: Jones arrived on a Sunday in September.
Hyp: Jones did arrive in September . (yes)
Jones NNP |
did VBD |
arrive VB |
September NNP |
. . |
|
Jones:NNP | 0.50 | 15.00 | 15.00 | 10.50 | 20.00 |
arrived:VBD | 15.50 | 7.47 | 0.50 | 15.50 | 20.00 |
a:DT | 20.50 | 20.00 | 20.00 | 20.50 | 10.00 |
Sunday:NNP | 15.00 | 10.20 | 15.50 | 7.23 | 20.50 |
September:NNP | 15.00 | 14.19 | 15.50 | 0.00 | 20.50 |
.:. | 20.50 | 17.99 | 20.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.0000
Features matched: Adjunct.dropPosCxt: text adjunct "Sunday" of "arrived" dropped on aligned hyp word "arrive"; Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 09/01/1000; NullPunisher.aux: did
Hand-tuned score: 2.4500
Threshold: -11.4590
Txt: The president left after the diplomat arrived.
Hyp: The diplomat did arrive before the president left . (yes)
The DT |
diplomat NN |
did VBD |
arrive VB |
before IN |
the DT |
president NN |
left VBD |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 10.00 |
president:NN | 20.00 | 3.94 | 15.00 | 14.47 | 20.00 | 20.00 | 0.00 | 13.35 | 20.00 |
left:VBD | 20.00 | 14.34 | 7.37 | 9.62 | 20.00 | 20.00 | 13.35 | 0.00 | 19.46 |
after:IN | 20.00 | 20.00 | 20.00 | 20.00 | 0.00 | 17.88 | 20.00 | 20.00 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 15.00 | 13.56 | 20.00 | 20.00 | 3.94 | 14.34 | 19.87 |
arrived:VBD | 20.00 | 13.41 | 7.47 | 0.50 | 20.00 | 20.00 | 13.72 | 6.03 | 20.00 |
.:. | 10.00 | 19.87 | 17.99 | 20.00 | 20.00 | 10.00 | 20.00 | 19.46 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -7.5000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "left vs. hyp "." <-punct-- "arrive", which aligned to text "arrived"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: No US congressman has visited Iraq since the war ended.
Hyp: Jones , a US Congressman , has visited Iraq after the war ended . (no)
Jones NNP |
, , |
a DT |
US_Congressman NNP |
, , |
has VBZ |
visited VBN |
Iraq NNP |
after IN |
the DT |
war NN |
ended VBD |
. . |
|
No:DT | 20.50 | 10.00 | 10.00 | 20.50 | 10.00 | 20.00 | 20.00 | 20.50 | 20.00 | 10.00 | 20.00 | 20.00 | 10.00 |
US:NNP | 14.34 | 20.50 | 20.50 | 5.00 | 20.50 | 13.02 | 15.50 | 5.34 | 20.50 | 20.50 | 10.50 | 13.02 | 20.50 |
congressman:NN | 10.19 | 19.74 | 20.50 | 5.00 | 19.74 | 14.84 | 15.32 | 14.34 | 20.50 | 20.50 | 9.08 | 13.55 | 20.50 |
has:VBZ | 14.84 | 20.00 | 20.00 | 14.26 | 20.00 | 0.00 | 10.00 | 13.02 | 20.00 | 20.00 | 15.00 | 7.52 | 20.00 |
visited:VBN | 15.50 | 19.44 | 20.00 | 15.46 | 19.44 | 10.00 | 0.00 | 15.50 | 20.00 | 20.00 | 12.10 | 7.62 | 19.78 |
Iraq:NNP | 14.34 | 20.50 | 20.50 | 12.67 | 20.50 | 13.02 | 15.50 | 0.00 | 20.50 | 20.50 | 10.50 | 13.02 | 20.50 |
since:IN | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.50 | 0.00 | 20.00 | 20.00 | 20.00 | 20.00 |
the:DT | 20.50 | 10.00 | 10.00 | 20.50 | 10.00 | 20.00 | 20.00 | 20.50 | 17.88 | 0.00 | 20.00 | 20.00 | 10.00 |
war:NN | 10.50 | 20.00 | 20.00 | 10.46 | 20.00 | 15.00 | 12.10 | 10.50 | 20.00 | 20.00 | 0.00 | 12.44 | 19.45 |
ended:VBD | 9.59 | 18.30 | 20.00 | 14.26 | 18.30 | 7.52 | 7.62 | 13.02 | 20.00 | 20.00 | 12.44 | 0.00 | 20.00 |
.:. | 20.50 | 5.73 | 10.00 | 20.50 | 5.73 | 20.00 | 19.78 | 20.50 | 20.00 | 10.00 | 19.45 | 20.00 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -33.4591
Features matched: Adjunct.dropPosCxt: text adjunct "US" of "congressman" dropped on aligned hyp word "US_Congressman"; NullPunisher.article: a; NullPunisher.other: Jones; Quant.oneNo: [no,a[
Hand-tuned score: -5.6000
Threshold: -11.4590
Txt: No US congressman has visited Iraq since the war.
Hyp: Jones , a US Congressman , did visit Iraq before the war . (unknown)
Jones NNP |
, , |
a DT |
US_Congressman NNP |
, , |
did VBD |
visit VB |
Iraq NNP |
the DT |
war NN |
. . |
|
No:DT | 20.50 | 10.00 | 10.00 | 20.50 | 10.00 | 20.00 | 20.00 | 20.50 | 10.00 | 20.00 | 10.00 |
US:NNP | 14.34 | 20.50 | 20.50 | 5.00 | 20.50 | 15.50 | 15.50 | 5.34 | 20.50 | 10.50 | 20.50 |
congressman:NN | 10.19 | 19.74 | 20.50 | 5.00 | 19.74 | 14.41 | 15.50 | 14.34 | 20.50 | 9.08 | 20.50 |
has:VBZ | 14.84 | 20.00 | 20.00 | 14.26 | 20.00 | 7.53 | 10.00 | 13.02 | 20.00 | 15.00 | 20.00 |
visited:VBN | 15.50 | 19.44 | 20.00 | 15.46 | 19.44 | 7.62 | 0.31 | 15.50 | 20.00 | 12.10 | 19.78 |
Iraq:NNP | 14.34 | 20.50 | 20.50 | 12.67 | 20.50 | 15.50 | 15.50 | 0.00 | 20.50 | 10.50 | 20.50 |
the:DT | 20.50 | 10.00 | 10.00 | 20.50 | 10.00 | 20.00 | 20.00 | 20.50 | 0.00 | 20.00 | 10.00 |
war:NN | 10.50 | 20.00 | 20.00 | 10.46 | 20.00 | 12.69 | 12.10 | 10.50 | 20.00 | 0.00 | 19.45 |
.:. | 20.50 | 5.73 | 10.00 | 20.50 | 5.73 | 17.99 | 20.00 | 20.50 | 10.00 | 19.45 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -36.7685
Features matched: Adjunct.dropPosCxt: text adjunct "US" of "congressman" dropped on aligned hyp word "US_Congressman"; NullPunisher.aux: did; NullPunisher.other: Jones; NullPunisher.article: a; Quant.oneNo: [no,a[; Structure.parentsMismatch: args have different parents, different relations: text "war" <-prep_since-- "Iraq" vs. hyp "war" <-prep_before-- "visit", which aligned to text "visited"
Hand-tuned score: -8.6500
Threshold: -11.4590
Txt: No US congressman visited Iraq until the war.
Hyp: Some US congressman did visit Iraq before the war . (no)
Some DT |
US NNP |
congressman NN |
did VBD |
visit VB |
Iraq NNP |
the DT |
war NN |
. . |
|
No:DT | 10.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 | 20.00 | 10.00 |
US:NNP | 20.50 | 0.00 | 9.84 | 15.50 | 15.50 | 5.34 | 20.50 | 10.50 | 20.50 |
congressman:NN | 20.00 | 9.84 | 0.00 | 13.91 | 15.00 | 9.84 | 20.00 | 8.58 | 20.00 |
visited:VBD | 20.00 | 15.50 | 14.82 | 7.62 | 0.31 | 15.50 | 20.00 | 12.10 | 19.78 |
Iraq:NNP | 20.50 | 5.34 | 9.84 | 15.50 | 15.50 | 0.00 | 20.50 | 10.50 | 20.50 |
the:DT | 10.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.50 | 0.00 | 20.00 | 10.00 |
war:NN | 20.00 | 10.50 | 8.58 | 12.69 | 12.10 | 10.50 | 20.00 | 0.00 | 19.45 |
.:. | 10.00 | 20.50 | 20.00 | 17.99 | 20.00 | 20.50 | 10.00 | 19.45 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: dontknow (INCORRECT)
Justification:
Alignment score: -12.3094
Features matched: Antonym.samePol: matching polarity with antonyms: Some & No; NullPunisher.aux: did; Quant.oneNo: [no,some[; Structure.relMismatch: text "war" is prep_until of "visited" while hyp "war" is prep_before of "visit" which aligned to text "visited"
Hand-tuned score: -14.0500
Threshold: -11.4590
Txt: Some students arrived at the school on Sunday.
Hyp: There were some students at the school on Sunday . (yes)
There EX |
were VBD |
some DT |
students NNS |
the DT |
school NN |
Sunday NNP |
. . |
|
Some:DT | 10.00 | 20.00 | 0.00 | 20.00 | 10.00 | 20.00 | 20.50 | 10.00 |
students:NNS | 20.00 | 14.34 | 20.00 | 0.00 | 20.00 | 0.75 | 10.50 | 20.00 |
arrived:VBD | 20.00 | 10.00 | 20.00 | 14.29 | 20.00 | 13.50 | 15.50 | 20.00 |
the:DT | 10.00 | 20.00 | 10.00 | 20.00 | 0.00 | 20.00 | 20.50 | 10.00 |
school:NN | 20.00 | 14.34 | 20.00 | 0.75 | 20.00 | 0.00 | 7.73 | 19.99 |
Sunday:NNP | 20.50 | 15.50 | 20.50 | 10.50 | 20.50 | 7.73 | 0.00 | 20.50 |
.:. | 10.00 | 20.00 | 10.00 | 20.00 | 10.00 | 19.99 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -15.0000
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/1000; NullPunisher.functionWord: There; Quant.contract: [some,some]; RootEntailment.poorlyAlignedRoot: "were" aligned badly to "arrived"
Hand-tuned score: 0.9000
Threshold: -11.4590
Txt: No students arrived at the school on Sunday.
Hyp: There were some students at the school on Sunday . (unknown)
There EX |
were VBD |
some DT |
students NNS |
the DT |
school NN |
Sunday NNP |
. . |
|
No:DT | 10.00 | 20.00 | 10.00 | 20.00 | 10.00 | 20.00 | 20.50 | 10.00 |
students:NNS | 20.00 | 14.34 | 20.00 | 0.00 | 20.00 | 0.75 | 10.50 | 20.00 |
arrived:VBD | 20.00 | 10.00 | 20.00 | 14.29 | 20.00 | 13.50 | 15.50 | 20.00 |
the:DT | 10.00 | 20.00 | 10.00 | 20.00 | 0.00 | 20.00 | 20.50 | 10.00 |
school:NN | 20.00 | 14.34 | 20.00 | 0.75 | 20.00 | 0.00 | 7.73 | 19.99 |
Sunday:NNP | 20.50 | 15.50 | 20.50 | 10.50 | 20.50 | 7.73 | 0.00 | 20.50 |
.:. | 10.00 | 20.00 | 10.00 | 20.00 | 10.00 | 19.99 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -25.0000
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/1000; NullPunisher.functionWord: There; NullPunisher.other: some; Quant.oneNo: [no,some[; RootEntailment.poorlyAlignedRoot: "were" aligned badly to "arrived"
Hand-tuned score: -7.1000
Threshold: -11.4590
Txt: There were no students at the school on Sunday.
Hyp: Some students did arrive at the school on Sunday . (no)
Some DT |
students NNS |
did VBD |
arrive VB |
the DT |
school NN |
Sunday NNP |
. . |
|
There:EX | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.50 | 10.00 |
were:VBD | 20.00 | 14.34 | 6.07 | 10.00 | 20.00 | 14.34 | 15.50 | 20.00 |
no:DT | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.50 | 10.00 |
students:NNS | 20.00 | 0.00 | 14.74 | 14.49 | 20.00 | 0.75 | 10.50 | 20.00 |
the:DT | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.50 | 10.00 |
school:NN | 20.00 | 0.75 | 10.44 | 15.00 | 20.00 | 0.00 | 7.73 | 19.99 |
Sunday:NNP | 20.50 | 10.50 | 10.20 | 15.50 | 20.50 | 7.73 | 0.00 | 20.50 |
.:. | 10.00 | 20.00 | 17.99 | 20.00 | 10.00 | 19.99 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -23.0000
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/1000; NullPunisher.other: Some; NullPunisher.aux: did; Quant.oneNo: [no,some[; RootEntailment.poorlyAlignedRoot: "arrive" aligned badly to "were"; Structure.argsMismatch: args have different parents but same relations: text "school" <-prep_at-- "students vs. hyp "school" <-prep_at-- "arrive", which aligned to text "were"
Hand-tuned score: -10.0500
Threshold: -11.4590
Txt: The diplomat left Baghdad last week.
Hyp: The diplomat has been to Baghdad . (yes)
The DT |
diplomat NN |
has VBZ |
been VBN |
Baghdad NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 14.34 | 14.34 | 9.84 | 19.87 |
left:VBD | 20.00 | 14.34 | 7.52 | 9.34 | 11.79 | 19.46 |
Baghdad:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
last:JJ | 20.50 | 11.45 | 11.19 | 10.83 | 16.34 | 20.50 |
week:NN | 20.50 | 10.50 | 14.19 | 15.50 | 15.00 | 17.43 |
.:. | 10.00 | 19.87 | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -12.3420
Features matched: Adjunct.dropPosCxt: text adjunct "week" of "left" dropped on aligned hyp word "been"; NullPunisher.aux: has; RootEntailment.poorlyAlignedRoot: "been" aligned badly to "left"; Structure.relMismatch: text "Baghdad" is dobj of "left" while hyp "Baghdad" is prep_to of "been" which aligned to text "left"
Hand-tuned score: -1.5500
Threshold: -11.4590
Txt: The diplomat will arrive in Baghdad next week.
Hyp: The diplomat has been to Baghdad . (unknown)
The DT |
diplomat NN |
has VBZ |
been VBN |
Baghdad NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 14.34 | 14.34 | 9.84 | 19.87 |
will:MD | 10.00 | 20.00 | 18.69 | 20.00 | 20.50 | 10.00 |
arrive:VB | 20.00 | 13.56 | 10.00 | 10.00 | 15.50 | 20.00 |
Baghdad:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
next:JJ | 20.00 | 11.96 | 11.96 | 11.96 | 12.46 | 20.00 |
week:NN | 20.00 | 10.00 | 13.69 | 15.00 | 10.50 | 16.93 |
.:. | 10.00 | 19.87 | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -12.0000
Features matched: Adjunct.dropPosCxt: text adjunct "week" of "arrive" dropped on aligned hyp word "been"; NullPunisher.aux: has; RootEntailment.poorlyAlignedRoot: "been" aligned badly to "arrive"; Structure.relMismatch: text "Baghdad" is prep_in of "arrive" while hyp "Baghdad" is prep_to of "been" which aligned to text "arrive"
Hand-tuned score: -1.5500
Threshold: -11.4590
Txt: The president knows that the diplomat left Baghdad.
Hyp: The diplomat has been to Baghdad . (yes)
The DT |
diplomat NN |
has VBZ |
been VBN |
Baghdad NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
president:NN | 20.00 | 3.94 | 14.34 | 14.34 | 9.84 | 20.00 |
knows:VBZ | 20.00 | 13.88 | 10.00 | 8.07 | 15.50 | 20.00 |
that:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.50 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 14.34 | 14.34 | 9.84 | 19.87 |
left:VBD | 20.00 | 14.34 | 7.52 | 9.34 | 11.79 | 19.46 |
Baghdad:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
.:. | 10.00 | 19.87 | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -13.0669
Features matched: NullPunisher.aux: has; RootEntailment.poorlyAlignedRoot: "been" aligned badly to "knows"; Structure.argsMismatch: args have different parents but same relations: text "diplomat" <-nsubj-- "left vs. hyp "diplomat" <-nsubj-- "been", which aligned to text "knows" args have different parents, different relations: text "Baghdad" <-dobj-- "left" vs. hyp "Baghdad" <-prep_to-- "been", which aligned to text "knows"
Hand-tuned score: -4.0500
Threshold: -11.4590
Txt: The president hasn't gone to Iraq since the diplomat left Baghdad.
Hyp: The diplomat has been to Baghdad . (yes)
The DT |
diplomat NN |
has VBZ |
been VBN |
Baghdad NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
president:NN | 20.00 | 3.94 | 14.34 | 14.34 | 9.84 | 20.00 |
has:VBZ | 20.00 | 14.34 | 0.00 | 9.34 | 13.02 | 20.00 |
n't:RB | 20.00 | 14.17 | 19.96 | 19.96 | 15.46 | 17.90 |
gone:VBN | 20.00 | 13.08 | 8.69 | 6.07 | 14.84 | 19.35 |
Iraq:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 2.00 | 20.50 |
since:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.50 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 14.34 | 14.34 | 9.84 | 19.87 |
left:VBD | 20.00 | 14.34 | 7.52 | 9.34 | 11.79 | 19.46 |
Baghdad:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
.:. | 10.00 | 19.87 | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -10.0708
Features matched: Adjunct.diffPol: hyp and txt have different polarity; Polarity.txtNegMarker: "gone": neg; RootEntailment.poorlyAlignedRoot: "been" aligned badly to "gone"; Structure.argsMismatch: args have different parents but same relations: text "diplomat" <-nsubj-- "left vs. hyp "diplomat" <-nsubj-- "been", which aligned to text "gone" args have different parents, different relations: text "Baghdad" <-dobj-- "left" vs. hyp "Baghdad" <-prep_to-- "been", which aligned to text "gone"
Hand-tuned score: -9.0000
Threshold: -11.4590
Txt: The president hasn't gone to Iraq since the diplomat left Baghdad.
Hyp: The president has been to Iraq . (unknown)
The DT |
president NN |
has VBZ |
been VBN |
Iraq NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
president:NN | 20.00 | 0.00 | 14.34 | 14.34 | 9.84 | 20.00 |
has:VBZ | 20.00 | 14.34 | 0.00 | 9.34 | 13.02 | 20.00 |
n't:RB | 20.00 | 14.96 | 19.96 | 19.96 | 15.46 | 17.90 |
gone:VBN | 20.00 | 12.72 | 8.69 | 6.07 | 14.84 | 19.35 |
Iraq:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
since:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.50 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
diplomat:NN | 20.00 | 3.94 | 14.34 | 14.34 | 9.84 | 19.87 |
left:VBD | 20.00 | 13.35 | 7.52 | 9.34 | 12.61 | 19.46 |
Baghdad:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 2.00 | 20.50 |
.:. | 10.00 | 20.00 | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -6.0708
Features matched: Adjunct.diffPol: hyp and txt have different polarity; Polarity.txtNegMarker: "gone": neg; RootEntailment.poorlyAlignedRoot: "been" aligned badly to "gone"
Hand-tuned score: -6.0000
Threshold: -11.4590
Txt: The diplomat didn't manage to leave Baghdad.
Hyp: The diplomat has been to Baghdad . (yes)
The DT |
diplomat NN |
has VBZ |
been VBN |
Baghdad NNP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 14.34 | 14.34 | 9.84 | 19.87 |
did:VBD | 20.00 | 15.00 | 7.53 | 6.07 | 15.50 | 17.99 |
n't:RB | 20.00 | 14.17 | 19.96 | 19.96 | 15.46 | 17.90 |
manage:VB | 20.00 | 15.00 | 10.00 | 8.07 | 15.50 | 19.98 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
leave:VB | 20.00 | 15.00 | 8.69 | 7.74 | 15.50 | 19.32 |
Baghdad:NNP | 20.50 | 9.84 | 13.02 | 14.84 | 0.00 | 20.50 |
.:. | 10.00 | 19.87 | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -11.0669
Features matched: Adjunct.diffPol: hyp and txt have different polarity; Polarity.txtNegMarker: "manage": neg; NullPunisher.aux: has; RootEntailment.poorlyAlignedRoot: "been" aligned badly to "manage"; Structure.parentsMismatch: args have different parents, different relations: text "Baghdad" <-dobj-- "leave" vs. hyp "Baghdad" <-prep_to-- "been", which aligned to text "manage"
Hand-tuned score: -9.0500
Threshold: -11.4590
Txt: The diplomat hasn't managed to leave Baghdad.
Hyp: The diplomat is in Baghdad now . (yes)
The DT |
diplomat NN |
is VBZ |
Baghdad NNP |
now RB |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.50 | 20.00 | 10.00 |
diplomat:NN | 20.00 | 0.00 | 14.34 | 9.84 | 15.00 | 19.87 |
has:VBZ | 20.00 | 14.34 | 8.64 | 13.02 | 18.69 | 20.00 |
n't:RB | 20.00 | 14.17 | 19.96 | 15.46 | 9.96 | 17.90 |
managed:VBN | 20.00 | 15.00 | 8.07 | 15.50 | 20.00 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.50 | 20.00 | 10.00 |
leave:VB | 20.00 | 15.00 | 7.74 | 15.50 | 18.69 | 19.32 |
Baghdad:NNP | 20.50 | 9.84 | 14.84 | 0.00 | 15.50 | 20.50 |
.:. | 10.00 | 19.87 | 20.00 | 20.50 | 20.00 | 0.00 |
NO_WORD | 1.00 | 10.00 | 10.00 | 10.00 | 9.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -19.0669
Features matched: Adjunct.diffPol: hyp and txt have different polarity; Polarity.txtNegMarker: "managed": neg; NullPunisher.other: now; RootEntailment.poorlyAlignedRoot: "is" aligned badly to "managed"; Structure.parentsMismatch: args have different parents, different relations: text "Baghdad" <-dobj-- "leave" vs. hyp "Baghdad" <-prep_in-- "is", which aligned to text "managed"
Hand-tuned score: -10.0000
Threshold: -11.4590
Txt: The room was full of intelligent women.
Hyp: The room was full of women . (yes)
The DT |
room NN |
was VBD |
full JJ |
women NNS |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.00 | 10.00 |
room:NN | 20.00 | 0.00 | 14.34 | 10.93 | 8.13 | 19.15 |
was:VBD | 20.00 | 14.34 | 0.00 | 12.00 | 14.34 | 20.00 |
full:JJ | 20.00 | 10.93 | 12.00 | 0.00 | 11.15 | 17.26 |
intelligent:JJ | 20.00 | 11.96 | 11.96 | 9.96 | 9.83 | 19.37 |
women:NNS | 20.00 | 8.13 | 14.34 | 11.15 | 0.00 | 19.64 |
.:. | 10.00 | 19.15 | 20.00 | 17.26 | 19.64 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: 0.0000
Features matched: Adjunct.dropPosCxt: text adjunct "intelligent" of "women" dropped on aligned hyp word "women"; Adjunct.dropPosCxt&Align.veryGood:
Hand-tuned score: 2.0000
Threshold: -11.4590
Txt: The room was full of women.
Hyp: The room was full of intelligent women . (unknown)
The DT |
room NN |
was VBD |
full JJ |
intelligent JJ |
women NNS |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 10.00 |
room:NN | 20.00 | 0.00 | 14.34 | 10.93 | 11.96 | 8.13 | 19.15 |
was:VBD | 20.00 | 14.34 | 0.00 | 12.00 | 11.96 | 14.34 | 20.00 |
full:JJ | 20.00 | 10.93 | 12.00 | 0.00 | 9.96 | 11.15 | 17.26 |
women:NNS | 20.00 | 8.13 | 14.34 | 11.15 | 9.83 | 0.00 | 19.64 |
.:. | 10.00 | 19.15 | 20.00 | 17.26 | 19.37 | 19.64 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 9.00 | 9.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -9.0000
Features matched: Adjunct.addPosCxt: hyp added intelligent[intelligent-JJ]; NullPunisher.other: intelligent
Hand-tuned score: -1.0000
Threshold: -11.4590
Txt: Children are not admitted to the theatre.
Hyp: Small children are admitted to the theater . (no)
Small JJ |
children NNS |
are VBP |
admitted VBN |
the DT |
theater NN |
. . |
|
Children:NNP | 11.34 | 0.00 | 15.00 | 15.00 | 20.00 | 8.95 | 20.00 |
are:VBP | 10.69 | 15.00 | 0.00 | 10.00 | 20.00 | 15.00 | 20.00 |
not:RB | 11.96 | 14.96 | 19.96 | 19.96 | 20.00 | 14.96 | 20.00 |
admitted:VBN | 12.00 | 12.85 | 10.00 | 0.00 | 20.00 | 15.00 | 19.33 |
the:DT | 20.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
theater:NN | 11.34 | 8.95 | 15.00 | 15.00 | 20.00 | 0.00 | 20.00 |
.:. | 20.00 | 19.49 | 20.00 | 19.33 | 10.00 | 20.00 | 0.00 |
NO_WORD | 9.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -9.0000
Features matched: Adjunct.diffPol: hyp and txt have different polarity; Polarity.txtNegMarker: "admitted": neg; NullPunisher.other: Small
Hand-tuned score: -5.0000
Threshold: -11.4590
Txt: Small children are not admitted to the theatre.
Hyp: Children are admitted to the theater . (unknown)
Children NNP |
are VBP |
admitted VBN |
the DT |
theater NN |
. . |
|
Small:JJ | 11.34 | 10.69 | 12.00 | 20.00 | 11.34 | 20.00 |
children:NNS | 0.00 | 15.00 | 12.85 | 20.00 | 8.95 | 19.49 |
are:VBP | 15.00 | 0.00 | 10.00 | 20.00 | 15.00 | 20.00 |
not:RB | 14.96 | 19.96 | 19.96 | 20.00 | 14.96 | 20.00 |
admitted:VBN | 15.00 | 10.00 | 0.00 | 20.00 | 15.00 | 19.33 |
the:DT | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
theater:NN | 8.95 | 15.00 | 15.00 | 20.00 | 0.00 | 20.00 |
.:. | 20.00 | 20.00 | 19.33 | 10.00 | 20.00 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: 0.0000
Features matched: Adjunct.diffPol: hyp and txt have different polarity; Polarity.txtNegMarker: "admitted": neg
Hand-tuned score: -4.0000
Threshold: -11.4590
Txt: All companies have to file annual reports.
Hyp: All Fortune 500 companies do have to file annual reports . (yes)
All DT |
Fortune JJ |
500 CD |
companies NNS |
do VBP |
have VB |
to TO |
file VB |
annual JJ |
reports NNS |
. . |
|
All:DT | 0.00 | 20.00 | 20.50 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 |
companies:NNS | 20.00 | 9.44 | 19.02 | 0.00 | 14.52 | 12.80 | 20.00 | 13.13 | 10.11 | 7.80 | 19.68 |
have:VBP | 20.00 | 12.00 | 20.50 | 12.80 | 6.02 | 0.00 | 20.00 | 7.02 | 10.11 | 12.80 | 20.00 |
to:TO | 10.00 | 20.00 | 20.50 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
file:VB | 20.00 | 12.00 | 19.19 | 13.13 | 7.45 | 7.02 | 20.00 | 0.00 | 10.03 | 12.37 | 20.00 |
annual:JJ | 20.00 | 10.00 | 19.41 | 10.11 | 12.00 | 10.11 | 20.00 | 10.03 | 0.00 | 10.23 | 20.00 |
reports:NNS | 20.00 | 12.00 | 19.19 | 7.80 | 12.69 | 12.80 | 20.00 | 12.37 | 10.23 | 0.00 | 19.70 |
.:. | 10.00 | 20.00 | 19.65 | 19.68 | 18.81 | 20.00 | 10.00 | 20.00 | 20.00 | 19.70 | 0.00 |
NO_WORD | 10.00 | 9.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -20.0000
Features matched: Adjunct.addAllCxt: all cxt -- hyp adds 500[500-CD];, hyp added 500[500-CD]; Modal.weakYes: necessary -> necessary; NullPunisher.aux: do; NullPunisher.other: Fortune; NullPunisher.other: 500; Quant.contract: [all,all]
Hand-tuned score: 3.9500
Threshold: -11.4590
Txt: All Fortune 500 companies have to file annual reports.
Hyp: All companies do have to file annual reports . (unknown)
All DT |
companies NNS |
do VBP |
have VB |
to TO |
file VB |
annual JJ |
reports NNS |
. . |
|
All:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 |
Fortune:JJ | 20.00 | 9.44 | 12.00 | 12.00 | 20.00 | 12.00 | 10.00 | 12.00 | 20.00 |
500:CD | 20.50 | 19.02 | 19.19 | 20.50 | 20.50 | 19.19 | 19.41 | 19.19 | 19.65 |
companies:NNS | 20.00 | 0.00 | 14.52 | 12.80 | 20.00 | 13.13 | 10.11 | 7.80 | 19.68 |
have:VBP | 20.00 | 12.80 | 6.02 | 0.00 | 20.00 | 7.02 | 10.11 | 12.80 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
file:VB | 20.00 | 13.13 | 7.45 | 7.02 | 20.00 | 0.00 | 10.03 | 12.37 | 20.00 |
annual:JJ | 20.00 | 10.11 | 12.00 | 10.11 | 20.00 | 10.03 | 0.00 | 10.23 | 20.00 |
reports:NNS | 20.00 | 7.80 | 12.69 | 12.80 | 20.00 | 12.37 | 10.23 | 0.00 | 19.70 |
.:. | 10.00 | 19.68 | 18.81 | 20.00 | 10.00 | 20.00 | 20.00 | 19.70 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 9.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -1.0000
Features matched: Adjunct.dropAllCxt: all cxt -- hyp drops adjunct 500 of companies aligned to hyp companies, text adjunct "500" of "companies" dropped on aligned hyp word "companies"; Modal.weakYes: necessary -> necessary; NullPunisher.aux: do; Quant.contract: [all,all]
Hand-tuned score: -0.0500
Threshold: -11.4590
Txt: All companies have to file annual reports to the SEC.
Hyp: All companies do have to file annual reports . (yes)
All DT |
companies NNS |
do VBP |
have VB |
to TO |
file VB |
annual JJ |
reports NNS |
. . |
|
All:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 |
companies:NNS | 20.00 | 0.00 | 14.52 | 12.80 | 20.00 | 13.13 | 10.11 | 7.80 | 19.68 |
have:VBP | 20.00 | 12.80 | 6.02 | 0.00 | 20.00 | 7.02 | 10.11 | 12.80 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
file:VB | 20.00 | 13.13 | 7.45 | 7.02 | 20.00 | 0.00 | 10.03 | 12.37 | 20.00 |
annual:JJ | 20.00 | 10.11 | 12.00 | 10.11 | 20.00 | 10.03 | 0.00 | 10.23 | 20.00 |
reports:NNS | 20.00 | 7.80 | 12.69 | 12.80 | 20.00 | 12.37 | 10.23 | 0.00 | 19.70 |
the:DT | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 |
SEC:NNP | 20.50 | 7.19 | 13.53 | 15.50 | 20.50 | 13.53 | 12.50 | 8.53 | 20.50 |
.:. | 10.00 | 19.68 | 18.81 | 20.00 | 10.00 | 20.00 | 20.00 | 19.70 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -1.0000
Features matched: Adjunct.dropPosCxt: text adjunct "SEC" of "file" dropped on aligned hyp word "file"; Modal.weakYes: necessary -> necessary; NullPunisher.aux: do; Quant.contract: [all,all]; Adjunct.dropPosCxt&Align.veryGood:
Hand-tuned score: 3.9500
Threshold: -11.4590
Txt: All companies have to file annual reports.
Hyp: All companies do have to file annual reports to the SEC . (unknown)
All DT |
companies NNS |
do VBP |
have VB |
to TO |
file VB |
annual JJ |
reports NNS |
the DT |
SEC NNP |
. . |
|
All:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.50 | 10.00 |
companies:NNS | 20.00 | 0.00 | 14.52 | 12.80 | 20.00 | 13.13 | 10.11 | 7.80 | 20.00 | 7.19 | 19.68 |
have:VBP | 20.00 | 12.80 | 6.02 | 0.00 | 20.00 | 7.02 | 10.11 | 12.80 | 20.00 | 15.50 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.50 | 10.00 |
file:VB | 20.00 | 13.13 | 7.45 | 7.02 | 20.00 | 0.00 | 10.03 | 12.37 | 20.00 | 13.53 | 20.00 |
annual:JJ | 20.00 | 10.11 | 12.00 | 10.11 | 20.00 | 10.03 | 0.00 | 10.23 | 20.00 | 12.50 | 20.00 |
reports:NNS | 20.00 | 7.80 | 12.69 | 12.80 | 20.00 | 12.37 | 10.23 | 0.00 | 20.00 | 8.53 | 19.70 |
.:. | 10.00 | 19.68 | 18.81 | 20.00 | 10.00 | 20.00 | 20.00 | 19.70 | 10.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 9.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -11.1929
Features matched: Modal.weakYes: necessary -> necessary; NullPunisher.article: the; NullPunisher.aux: do; Quant.contract: [all,all]; Quant.contract: [all,the]
Hand-tuned score: 3.8500
Threshold: -11.4590
Txt: No delegates finished the report.
Hyp: Some delegate did finish the report on_time . (no)
Some DT |
delegate NN |
did VBD |
finish VB |
the DT |
report NN |
on_time NN |
. . |
|
No:DT | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 10.00 |
delegates:NNS | 20.00 | 0.31 | 15.00 | 13.85 | 20.00 | 9.57 | 9.96 | 20.00 |
finished:VBD | 20.00 | 14.18 | 5.51 | 0.50 | 20.00 | 11.89 | 12.66 | 18.93 |
the:DT | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 10.00 |
report:NN | 20.00 | 9.11 | 12.69 | 11.89 | 20.00 | 0.00 | 8.45 | 19.87 |
.:. | 10.00 | 20.00 | 17.99 | 18.26 | 10.00 | 19.87 | 20.00 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -22.2555
Features matched: NullPunisher.other: Some; NullPunisher.aux: did; Quant.oneNo: [no,some[
Hand-tuned score: -6.0500
Threshold: -11.4590
Txt: The US troops stayed in Iraq although the war was over.
Hyp: The war was over . (yes)
The DT |
war NN |
was VBD |
over RP |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 10.00 | 10.00 |
US:NNP | 20.50 | 10.50 | 11.83 | 20.50 | 20.50 |
troops:NNS | 20.00 | 5.07 | 15.00 | 20.00 | 20.00 |
stayed:VBD | 20.00 | 12.44 | 9.34 | 18.69 | 18.18 |
Iraq:NNP | 20.50 | 10.50 | 11.83 | 20.50 | 20.50 |
although:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 10.00 | 10.00 |
war:NN | 20.00 | 0.00 | 15.00 | 20.00 | 19.45 |
was:VBD | 20.00 | 15.00 | 0.00 | 20.00 | 20.00 |
over:RP | 10.00 | 20.00 | 20.00 | 0.00 | 10.00 |
.:. | 10.00 | 19.45 | 20.00 | 10.00 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.0000
Features matched: Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "stayed vs. hyp "." <-punct-- "over", which aligned to text "over"
Hand-tuned score: -2.0000
Threshold: -11.4590
Txt: Since it was cold, he closed the window.
Hyp: It was cold . (yes)
It PRP |
was VBD |
cold JJ |
. . |
|
Since:IN | 20.00 | 20.00 | 20.00 | 20.00 |
it:PRP | 0.00 | 15.00 | 15.00 | 20.00 |
was:VBD | 15.00 | 0.00 | 11.34 | 20.00 |
cold:JJ | 15.00 | 11.34 | 0.00 | 19.61 |
,:, | 20.00 | 20.00 | 20.00 | 5.73 |
he:PRP | 10.00 | 15.00 | 15.00 | 20.00 |
closed:VBD | 15.00 | 10.00 | 9.84 | 19.49 |
the:DT | 20.00 | 20.00 | 20.00 | 10.00 |
window:NN | 12.00 | 12.52 | 9.28 | 19.62 |
.:. | 20.00 | 20.00 | 19.61 | 0.00 |
NO_WORD | 10.00 | 1.00 | 9.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.0000
Features matched: Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "closed vs. hyp "." <-punct-- "cold", which aligned to text "cold"
Hand-tuned score: -2.0000
Threshold: -11.4590
Txt: John didn't visit us after he returned from Spain.
Hyp: John did return from Spain . (yes)
John NNP |
did VBD |
return NN |
Spain NNP |
. . |
|
John:NNP | 0.00 | 13.35 | 7.27 | 14.34 | 20.50 |
did:VBD | 13.35 | 0.00 | 10.85 | 15.50 | 17.99 |
n't:RB | 15.46 | 13.27 | 12.74 | 15.46 | 17.90 |
visit:VB | 15.50 | 7.62 | 12.10 | 15.50 | 20.00 |
us:PRP | 12.50 | 15.00 | 12.00 | 12.50 | 20.00 |
after:IN | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 |
he:PRP | 12.50 | 15.00 | 12.00 | 12.50 | 20.00 |
returned:VBD | 12.27 | 6.77 | 0.31 | 14.84 | 19.41 |
Spain:NNP | 14.34 | 15.50 | 9.84 | 0.00 | 20.50 |
.:. | 20.50 | 17.99 | 19.01 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -8.3094
Features matched: Structure.argsMismatch: args have different parents but same relations: text "John" <-nsubj-- "visit vs. hyp "John" <-nsubj-- "did", which aligned to text "did" args have different parents but same relations: text "Spain" <-prep_from-- "returned vs. hyp "Spain" <-prep_from-- "did", which aligned to text "did" args have different parents but same relations: text "." <-punct-- "visit vs. hyp "." <-punct-- "did", which aligned to text "did" args have different parents, different relations: text "returned" <-advcl-- "visit" vs. hyp "return" <-dobj-- "did", which aligned to text "did"
Hand-tuned score: -2.0000
Threshold: -11.4590
Txt: Hanssen, who sold FBI secrets to the Russians, could face the death penalty.
Hyp: Hanssen did sell FBI secrets to the Russians . (yes)
Hanssen NNP |
did VBD |
sell VB |
FBI NNP |
secrets NNS |
the DT |
Russians NNPS |
. . |
|
Hanssen:NNP | 0.00 | 15.46 | 15.46 | 14.96 | 10.46 | 20.50 | 14.96 | 20.50 |
,:, | 20.50 | 19.80 | 19.98 | 20.50 | 20.00 | 10.00 | 20.50 | 5.73 |
who:WP | 12.50 | 15.00 | 15.00 | 12.50 | 12.00 | 20.00 | 12.50 | 20.00 |
sold:VBD | 15.46 | 7.69 | 0.50 | 15.50 | 13.55 | 20.00 | 15.50 | 19.42 |
FBI:NNP | 14.96 | 15.50 | 15.50 | 0.00 | 10.50 | 20.50 | 15.00 | 20.50 |
secrets:NNS | 10.46 | 12.85 | 14.18 | 10.50 | 0.00 | 20.00 | 8.35 | 20.00 |
the:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
Russians:NNPS | 14.96 | 13.35 | 15.50 | 15.00 | 8.35 | 20.50 | 0.00 | 20.50 |
,:, | 20.50 | 19.80 | 19.98 | 20.50 | 20.00 | 10.00 | 20.50 | 5.73 |
could:MD | 20.46 | 17.84 | 19.96 | 20.46 | 19.96 | 10.00 | 20.46 | 10.00 |
face:VB | 15.46 | 4.55 | 8.07 | 15.50 | 12.44 | 20.00 | 13.35 | 17.99 |
the:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
death_penalty:NN | 10.46 | 12.69 | 12.10 | 10.50 | 8.72 | 20.00 | 9.84 | 20.00 |
.:. | 20.50 | 17.99 | 19.05 | 20.50 | 20.00 | 10.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -3.5000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "Hanssen" <-nsubj-- "face vs. hyp "Hanssen" <-nsubj-- "sell", which aligned to text "sold" args have different parents but same relations: text "." <-punct-- "face vs. hyp "." <-punct-- "sell", which aligned to text "sold"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: The New York Times reported that Hanssen, who sold FBI secrets to the Russians, could face the death penalty.
Hyp: Hanssen did sell FBI secrets to the Russians . (yes)
Hanssen NNP |
did VBD |
sell VB |
FBI NNP |
secrets NNS |
the DT |
Russians NNPS |
. . |
|
The:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
New_York_Times:NNPS | 14.96 | 14.84 | 14.68 | 8.91 | 9.84 | 20.50 | 14.34 | 20.50 |
reported:VBD | 15.46 | 7.69 | 7.69 | 15.50 | 11.05 | 20.00 | 13.35 | 19.71 |
that:IN | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 |
Hanssen:NNP | 0.00 | 15.46 | 15.46 | 14.96 | 10.46 | 20.50 | 14.96 | 20.50 |
,:, | 20.50 | 19.80 | 19.98 | 20.50 | 20.00 | 10.00 | 20.50 | 5.73 |
who:WP | 12.50 | 15.00 | 15.00 | 12.50 | 12.00 | 20.00 | 12.50 | 20.00 |
sold:VBD | 15.46 | 7.69 | 0.50 | 15.50 | 13.55 | 20.00 | 15.50 | 19.42 |
FBI:NNP | 14.96 | 15.50 | 15.50 | 0.00 | 10.50 | 20.50 | 15.00 | 20.50 |
secrets:NNS | 10.46 | 12.85 | 14.18 | 10.50 | 0.00 | 20.00 | 8.35 | 20.00 |
the:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
Russians:NNPS | 14.96 | 13.35 | 15.50 | 15.00 | 8.35 | 20.50 | 0.00 | 20.50 |
,:, | 20.50 | 19.80 | 19.98 | 20.50 | 20.00 | 10.00 | 20.50 | 5.73 |
could:MD | 20.46 | 17.84 | 19.96 | 20.46 | 19.96 | 10.00 | 20.46 | 10.00 |
face:VB | 15.46 | 4.55 | 8.07 | 15.50 | 12.44 | 20.00 | 13.35 | 17.99 |
the:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
death_penalty:NN | 10.46 | 12.69 | 12.10 | 10.50 | 8.72 | 20.00 | 9.84 | 20.00 |
.:. | 20.50 | 17.99 | 19.05 | 20.50 | 20.00 | 10.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -3.5000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "Hanssen" <-nsubj-- "face vs. hyp "Hanssen" <-nsubj-- "sell", which aligned to text "sold" args have different parents but same relations: text "." <-punct-- "reported vs. hyp "." <-punct-- "sell", which aligned to text "sold"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: The New York Times reported that Hanssen sold FBI secrets to the Russians and could face the death penalty.
Hyp: Hanssen did sell FBI secrets to the Russians . (unknown)
Hanssen NNP |
did VBD |
sell VB |
FBI NNP |
secrets NNS |
the DT |
Russians NNPS |
. . |
|
The:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
New_York_Times:NNPS | 14.96 | 14.84 | 14.68 | 8.91 | 9.84 | 20.50 | 14.34 | 20.50 |
reported:VBD | 15.46 | 7.69 | 7.69 | 15.50 | 11.05 | 20.00 | 13.35 | 19.71 |
that:IN | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 |
Hanssen:NNP | 0.00 | 15.46 | 15.46 | 14.96 | 10.46 | 20.50 | 14.96 | 20.50 |
sold:VBD | 15.46 | 7.69 | 0.50 | 15.50 | 13.55 | 20.00 | 15.50 | 19.42 |
FBI:NNP | 14.96 | 15.50 | 15.50 | 0.00 | 10.50 | 20.50 | 15.00 | 20.50 |
secrets:NNS | 10.46 | 12.85 | 14.18 | 10.50 | 0.00 | 20.00 | 8.35 | 20.00 |
the:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
Russians:NNPS | 14.96 | 13.35 | 15.50 | 15.00 | 8.35 | 20.50 | 0.00 | 20.50 |
could:MD | 20.46 | 17.84 | 19.96 | 20.46 | 19.96 | 10.00 | 20.46 | 10.00 |
face:VB | 15.46 | 4.55 | 8.07 | 15.50 | 12.44 | 20.00 | 13.35 | 17.99 |
the:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 | 0.00 | 20.50 | 10.00 |
death_penalty:NN | 10.46 | 12.69 | 12.10 | 10.50 | 8.72 | 20.00 | 9.84 | 20.00 |
.:. | 20.50 | 17.99 | 19.05 | 20.50 | 20.00 | 10.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -3.5000
Features matched: Factive.unknownPassage: non factive text -- unknown: reported-VBD; NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "reported vs. hyp "." <-punct-- "sell", which aligned to text "sold"
Hand-tuned score: -1.5500
Threshold: -11.4590
Txt: Bush said that it was Khan who sold centrifuges to North Korea.
Hyp: Centrifuges were sold to North_Korea . (yes)
Centrifuges NNS |
were VBD |
sold VBN |
North_Korea NNP |
. . |
|
Bush:NNP | 9.45 | 14.84 | 12.74 | 7.61 | 20.50 |
said:VBD | 15.00 | 6.24 | 7.80 | 15.00 | 18.58 |
that:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
it:PRP | 12.00 | 15.00 | 15.00 | 12.00 | 20.00 |
was:VBD | 14.34 | 0.50 | 10.00 | 11.33 | 20.00 |
Khan:NNP | 8.53 | 14.84 | 15.50 | 9.52 | 20.50 |
who:WP | 12.00 | 15.00 | 15.00 | 12.00 | 20.00 |
sold:VBD | 15.00 | 7.80 | 0.00 | 15.00 | 19.42 |
centrifuges:NNS | 0.00 | 14.34 | 14.23 | 9.34 | 19.93 |
North_Korea:NNP | 9.84 | 14.84 | 15.50 | 0.50 | 20.50 |
.:. | 20.00 | 20.00 | 19.42 | 20.00 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -3.5000
Features matched: NullPunisher.aux: were; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "said vs. hyp "." <-punct-- "sold", which aligned to text "sold"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: Bush said that Khan sold centrifuges to North Korea.
Hyp: Centrifuges were sold to North_Korea . (unknown)
Centrifuges NNS |
were VBD |
sold VBN |
North_Korea NNP |
. . |
|
Bush:NNP | 9.45 | 14.84 | 12.74 | 7.61 | 20.50 |
said:VBD | 15.00 | 6.24 | 7.80 | 15.00 | 18.58 |
that:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
Khan:NNP | 8.53 | 14.84 | 15.50 | 9.52 | 20.50 |
sold:VBD | 15.00 | 7.80 | 0.00 | 15.00 | 19.42 |
centrifuges:NNS | 0.00 | 14.34 | 14.23 | 9.34 | 19.93 |
North_Korea:NNP | 9.84 | 14.84 | 15.50 | 0.50 | 20.50 |
.:. | 20.00 | 20.00 | 19.42 | 20.00 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -3.5000
Features matched: Factive.unknownPassage: non factive text -- unknown: said-VBD; NullPunisher.aux: were; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "said vs. hyp "." <-punct-- "sold", which aligned to text "sold"
Hand-tuned score: -1.5500
Threshold: -11.4590
Txt: What we found in Iraq was rusted shrapnel.
Hyp: We did find something in Iraq . (yes)
We PRP |
did VBD |
find VB |
something NN |
Iraq NNP |
. . |
|
What:WP | 10.00 | 15.00 | 15.00 | 12.00 | 12.50 | 20.00 |
we:PRP | 0.00 | 15.00 | 15.00 | 12.00 | 12.50 | 20.00 |
found:VBD | 15.00 | 6.26 | 0.50 | 15.00 | 15.50 | 19.57 |
Iraq:NNP | 12.50 | 15.50 | 15.50 | 9.84 | 0.00 | 20.50 |
was:VBD | 15.00 | 10.00 | 10.00 | 14.34 | 11.83 | 20.00 |
rusted:VBN | 15.00 | 7.62 | 7.61 | 14.34 | 14.84 | 20.00 |
shrapnel:JJ | 15.00 | 11.21 | 12.00 | 11.34 | 11.84 | 20.00 |
.:. | 20.00 | 17.99 | 18.14 | 20.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -13.5000
Features matched: NullPunisher.other: something; NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "rusted vs. hyp "." <-punct-- "find", which aligned to text "found"
Hand-tuned score: -3.0500
Threshold: -11.4590
Txt: The fact that Bin Laden was in Tora Bora led to the suspicion that the Afghan campaign was mismanaged.
Hyp: Bin_Laden was in Tora Bora . (yes)
Bin_Laden NNP |
was VBD |
Tora_Bora NNP |
. . |
|
The:DT | 20.00 | 20.00 | 20.50 | 10.00 |
fact:NN | 8.92 | 15.00 | 10.46 | 17.53 |
that:IN | 20.00 | 20.00 | 20.50 | 20.00 |
Bin_Laden:NNP | 0.50 | 14.84 | 14.96 | 20.50 |
was:VBD | 14.34 | 0.00 | 15.46 | 20.00 |
Tora_Bora:NNP | 10.46 | 15.46 | 0.00 | 20.50 |
led:VBD | 13.56 | 9.34 | 15.46 | 19.43 |
the:DT | 20.00 | 20.00 | 20.50 | 10.00 |
suspicion:NN | 9.34 | 15.00 | 10.46 | 19.99 |
that:IN | 20.00 | 20.00 | 20.50 | 20.00 |
the:DT | 20.00 | 20.00 | 20.50 | 10.00 |
Afghan:JJ | 10.55 | 11.84 | 16.96 | 20.50 |
campaign:NN | 10.00 | 15.00 | 10.46 | 19.85 |
was:VBD | 14.34 | 0.00 | 15.46 | 20.00 |
mismanaged:VBN | 15.00 | 10.00 | 15.46 | 20.00 |
.:. | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.5000
Features matched: Factive.factivePassage: factive entails : fact-NN; Location.mismatch: no clear info of matching: be(X, prep_in); Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "led vs. hyp "." <-punct-- "was", which aligned to text "was"
Hand-tuned score: -3.0000
Threshold: -11.4590
Txt: The fact that Bin Laden was in Tora Bora led to the suspicion that the Afghan campaign was mismanaged.
Hyp: The Afghan campaign was mismanaged . (unknown)
The DT |
Afghan JJ |
campaign NN |
was VBD |
mismanaged VBN |
. . |
|
The:DT | 0.00 | 20.50 | 20.00 | 20.00 | 20.00 | 10.00 |
fact:NN | 20.00 | 10.35 | 8.94 | 15.00 | 14.66 | 17.53 |
that:IN | 20.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 |
Bin_Laden:NNP | 20.50 | 15.05 | 10.50 | 14.84 | 15.50 | 20.50 |
was:VBD | 20.00 | 11.84 | 15.00 | 0.00 | 10.00 | 20.00 |
Tora_Bora:NNP | 20.50 | 16.96 | 10.46 | 15.46 | 15.46 | 20.50 |
led:VBD | 20.00 | 10.53 | 14.51 | 9.34 | 8.89 | 19.43 |
the:DT | 0.00 | 20.50 | 20.00 | 20.00 | 20.00 | 10.00 |
suspicion:NN | 20.00 | 11.19 | 8.40 | 15.00 | 12.80 | 19.99 |
that:IN | 20.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 |
the:DT | 0.00 | 20.50 | 20.00 | 20.00 | 20.00 | 10.00 |
Afghan:JJ | 20.50 | 0.00 | 12.50 | 11.84 | 12.50 | 20.50 |
campaign:NN | 20.00 | 12.50 | 0.00 | 15.00 | 14.12 | 19.85 |
was:VBD | 20.00 | 11.84 | 15.00 | 0.00 | 10.00 | 20.00 |
mismanaged:VBN | 20.00 | 12.50 | 14.12 | 10.00 | 0.00 | 20.00 |
.:. | 10.00 | 20.50 | 19.85 | 20.00 | 20.00 | 0.00 |
NO_WORD | 1.00 | 9.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.0000
Features matched: Factive.inPositiveEmbedding: embedded positive text; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "led vs. hyp "." <-punct-- "mismanaged", which aligned to text "mismanaged"
Hand-tuned score: -1.0000
Threshold: -11.4590
Txt: The paper concluded that the election had been rigged.
Hyp: The election was rigged . (unknown)
The DT |
election NN |
was VBD |
rigged VBN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
paper:NN | 20.00 | 8.35 | 14.34 | 12.12 | 18.64 |
concluded:VBD | 20.00 | 15.00 | 10.00 | 10.00 | 19.24 |
that:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
election:NN | 20.00 | 0.00 | 15.00 | 11.41 | 20.00 |
had:VBD | 20.00 | 15.00 | 9.34 | 5.73 | 20.00 |
been:VBN | 20.00 | 15.00 | 0.50 | 7.80 | 20.00 |
rigged:VBN | 20.00 | 11.41 | 9.34 | 0.00 | 20.00 |
.:. | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.5000
Features matched: Factive.unknownPassage: non factive text -- unknown: concluded-VBD; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "concluded vs. hyp "." <-punct-- "rigged", which aligned to text "rigged"
Hand-tuned score: -1.5000
Threshold: -11.4590
Txt: Ames was, as the press reported, a successful spy.
Hyp: Ames was a successful spy . (yes)
Ames NNP |
was VBD |
a DT |
successful JJ |
spy NN |
. . |
|
Ames:NNP | 0.00 | 15.46 | 20.50 | 12.46 | 10.46 | 20.50 |
was:VBD | 15.46 | 0.00 | 20.00 | 11.96 | 14.34 | 20.00 |
,:, | 20.50 | 20.00 | 10.00 | 19.58 | 20.00 | 5.73 |
the:DT | 20.50 | 20.00 | 10.00 | 20.00 | 20.00 | 10.00 |
press:NN | 10.46 | 14.34 | 20.00 | 11.96 | 8.50 | 19.26 |
reported:VBN | 15.46 | 10.00 | 20.00 | 11.96 | 14.05 | 19.71 |
,:, | 20.50 | 20.00 | 10.00 | 19.58 | 20.00 | 5.73 |
a:DT | 20.50 | 20.00 | 0.00 | 20.00 | 20.00 | 10.00 |
successful:JJ | 12.46 | 11.96 | 20.00 | 0.00 | 11.78 | 18.38 |
spy:NN | 10.46 | 14.34 | 20.00 | 11.78 | 0.00 | 20.00 |
.:. | 20.50 | 20.00 | 10.00 | 18.38 | 20.00 | 0.00 |
NO_WORD | 10.00 | 1.00 | 1.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -5.0000
Features matched: Factive.unknownPassage: non factive text -- unknown: reported-VBN; NullPunisher.aux: was; Quant.contract: [a,a]; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "reported vs. hyp "." <-punct-- "spy", which aligned to text "spy" args have different parents, different relations: text "Ames" <-nsubjpass-- "reported" vs. hyp "Ames" <-nsubj-- "spy", which aligned to text "spy"
Hand-tuned score: -0.5500
Threshold: -11.4590
Txt: The press reported that Ames was a successful spy.
Hyp: Ames was a successful spy . (unknown)
Ames NNP |
was VBD |
a DT |
successful JJ |
spy NN |
. . |
|
The:DT | 20.50 | 20.00 | 10.00 | 20.00 | 20.00 | 10.00 |
press:NN | 10.46 | 14.34 | 20.00 | 11.96 | 8.50 | 19.26 |
reported:VBD | 15.46 | 10.00 | 20.00 | 11.96 | 14.05 | 19.71 |
that:IN | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
Ames:NNP | 0.00 | 15.46 | 20.50 | 12.46 | 10.46 | 20.50 |
was:VBD | 15.46 | 0.00 | 20.00 | 11.96 | 14.34 | 20.00 |
a:DT | 20.50 | 20.00 | 0.00 | 20.00 | 20.00 | 10.00 |
successful:JJ | 12.46 | 11.96 | 20.00 | 0.00 | 11.78 | 18.38 |
spy:NN | 10.46 | 14.34 | 20.00 | 11.78 | 0.00 | 20.00 |
.:. | 20.50 | 20.00 | 10.00 | 18.38 | 20.00 | 0.00 |
NO_WORD | 10.00 | 1.00 | 1.00 | 9.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.0000
Features matched: Factive.unknownPassage: non factive text -- unknown: reported-VBD; Quant.contract: [a,a]; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "reported vs. hyp "." <-punct-- "spy", which aligned to text "spy"
Hand-tuned score: -0.5000
Threshold: -11.4590
Txt: The US forgot that the Afghans speak several different languages.
Hyp: The Afghans do speak several different languages . (yes)
The DT |
Afghans NNPS |
do VBP |
speak VB |
several JJ |
different JJ |
languages NNS |
. . |
|
The:DT | 0.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 10.00 |
US:NNP | 20.50 | 14.34 | 15.50 | 15.50 | 12.46 | 12.46 | 10.50 | 20.50 |
forgot:VBD | 20.00 | 15.50 | 8.48 | 9.43 | 11.96 | 11.96 | 15.00 | 19.56 |
that:IN | 20.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
the:DT | 0.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 10.00 |
Afghans:NNPS | 20.50 | 0.00 | 13.35 | 15.50 | 12.46 | 12.46 | 5.87 | 20.50 |
speak:VBP | 20.00 | 15.50 | 5.23 | 0.00 | 11.96 | 11.39 | 12.82 | 18.41 |
several:JJ | 20.00 | 12.46 | 11.96 | 11.96 | 0.00 | 9.96 | 11.96 | 20.00 |
different:JJ | 20.00 | 12.46 | 10.27 | 11.39 | 9.96 | 0.00 | 8.76 | 17.27 |
languages:NNS | 20.00 | 5.87 | 11.24 | 12.82 | 11.96 | 8.76 | 0.00 | 19.86 |
.:. | 10.00 | 20.50 | 18.81 | 18.41 | 20.00 | 17.27 | 19.86 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 9.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -3.0000
Features matched: Factive.negativeStatement: non factive text : forgot-VBD; NullPunisher.aux: do; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "forgot vs. hyp "." <-punct-- "speak", which aligned to text "speak"
Hand-tuned score: -7.0500
Threshold: -11.4590
Txt: Bush realized that the US Army had to be transformed to meet new threats.
Hyp: The US_Army did have to be transformed to meet new threats . (yes)
The DT |
US_Army NNP |
did VBD |
have VB |
to TO |
be VB |
transformed VBN |
to TO |
meet VB |
new JJ |
threats NNS |
. . |
|
Bush:NNP | 20.00 | 8.13 | 15.00 | 13.05 | 20.00 | 14.34 | 15.00 | 20.00 | 12.02 | 11.96 | 8.05 | 20.00 |
realized:VBD | 20.00 | 15.00 | 7.32 | 6.84 | 20.00 | 10.00 | 7.20 | 20.00 | 7.24 | 11.96 | 14.16 | 17.47 |
that:IN | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 |
US_Army:NNP | 20.50 | 0.50 | 15.50 | 15.17 | 20.50 | 15.17 | 15.50 | 20.50 | 15.50 | 12.46 | 10.17 | 20.50 |
had:VBD | 20.00 | 14.67 | 7.32 | 0.50 | 20.00 | 7.80 | 7.61 | 20.00 | 3.72 | 11.96 | 13.05 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
be:VB | 20.00 | 14.67 | 6.07 | 7.80 | 20.00 | 0.00 | 10.00 | 20.00 | 2.00 | 11.96 | 14.34 | 20.00 |
transformed:VBN | 20.00 | 15.00 | 7.62 | 7.61 | 20.00 | 10.00 | 0.00 | 20.00 | 7.61 | 10.33 | 14.61 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 0.00 | 20.00 | 20.00 | 20.00 | 10.00 |
meet:VB | 20.00 | 15.00 | 5.11 | 3.72 | 20.00 | 6.07 | 7.61 | 20.00 | 0.00 | 11.24 | 14.50 | 19.52 |
new:JJ | 20.00 | 11.96 | 11.96 | 11.96 | 20.00 | 11.96 | 10.33 | 20.00 | 11.24 | 0.00 | 11.96 | 20.00 |
threats:NNS | 20.00 | 9.67 | 12.85 | 13.05 | 20.00 | 14.34 | 14.61 | 20.00 | 14.50 | 11.96 | 0.00 | 19.03 |
.:. | 10.00 | 20.00 | 17.99 | 20.00 | 10.00 | 20.00 | 20.00 | 10.00 | 19.52 | 20.00 | 19.03 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 9.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -4.0000
Features matched: Factive.factivePassage: factive entails : realized-VBD; Modal.weakYes: necessary -> necessary; NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "US_Army" <-xsubj-- "transformed vs. hyp "US_Army" <-nsubj-- "have", which aligned to text "had" args have different parents but same relations: text "." <-punct-- "realized vs. hyp "." <-punct-- "have", which aligned to text "had"
Hand-tuned score: -0.0500
Threshold: -11.4590
Txt: Bush didn't realize that Afghanistan is land-locked.
Hyp: Afghanistan is land-locked . (yes)
Afghanistan NNP |
is VBZ |
land-locked JJ |
. . |
|
Bush:NNP | 7.61 | 14.34 | 11.96 | 20.00 |
did:VBD | 15.50 | 6.07 | 11.96 | 17.99 |
n't:RB | 15.46 | 19.96 | 11.96 | 17.90 |
realize:VB | 15.50 | 10.00 | 11.74 | 17.34 |
that:IN | 20.50 | 20.00 | 20.00 | 20.00 |
Afghanistan:NNP | 0.00 | 14.84 | 12.46 | 20.50 |
is:VBZ | 14.84 | 0.00 | 11.96 | 20.00 |
land:NN | 2.50 | 14.34 | 6.75 | 18.77 |
-:: | 20.50 | 20.00 | 20.00 | 10.00 |
locked:VBN | 14.84 | 9.34 | 6.75 | 19.17 |
.:. | 20.50 | 20.00 | 18.97 | 0.00 |
NO_WORD | 10.00 | 1.00 | 9.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -8.7474
Features matched: Adjunct.dropPosCxt: text adjunct "locked" of "land" dropped on aligned hyp word "land-locked"; Factive.factivePassage: factive entails : realize-VB; RootEntailment.poorlyAlignedRoot: "land-locked" aligned badly to "land"; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "realize vs. hyp "." <-punct-- "land-locked", which aligned to text "land"
Hand-tuned score: -2.5000
Threshold: -11.4590
Txt: There is a belief that the US will invade Syria.
Hyp: The US will invade Syria . (unknown)
The DT |
US NNP |
will MD |
invade VB |
Syria NNP |
. . |
|
There:EX | 10.00 | 20.50 | 10.00 | 20.00 | 20.50 | 10.00 |
is:VBZ | 20.00 | 14.84 | 20.00 | 6.70 | 14.84 | 20.00 |
a:DT | 10.00 | 20.50 | 10.00 | 20.00 | 20.50 | 10.00 |
belief:NN | 20.00 | 10.50 | 17.47 | 14.83 | 10.50 | 18.82 |
that:IN | 20.00 | 20.50 | 20.00 | 20.00 | 20.50 | 20.00 |
the:DT | 0.00 | 20.50 | 10.00 | 20.00 | 20.50 | 10.00 |
US:NNP | 20.50 | 0.00 | 20.50 | 15.50 | 5.34 | 20.50 |
will:MD | 10.00 | 20.50 | 0.00 | 20.00 | 20.50 | 10.00 |
invade:VB | 20.00 | 15.50 | 20.00 | 0.00 | 15.50 | 20.00 |
Syria:NNP | 20.50 | 5.34 | 20.50 | 15.50 | 0.00 | 20.50 |
.:. | 10.00 | 20.50 | 10.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.0000
Features matched: Factive.unknownPassage: non factive text -- unknown: belief-NN; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "is vs. hyp "." <-punct-- "invade", which aligned to text "invade"
Hand-tuned score: -1.5000
Threshold: -11.4590
Txt: It is not surprising that Bush has the lead in Ohio.
Hyp: Bush does have the lead in Ohio . (yes)
Bush NNP |
does VBZ |
have VB |
the DT |
lead NN |
Ohio NNP |
. . |
|
It:PRP | 12.50 | 15.00 | 15.00 | 20.00 | 12.00 | 12.50 | 20.00 |
is:VBZ | 14.84 | 9.34 | 7.80 | 20.00 | 9.39 | 14.84 | 20.00 |
not:RB | 15.46 | 19.96 | 19.96 | 20.00 | 14.96 | 15.46 | 20.00 |
surprising:JJ | 12.50 | 11.87 | 10.07 | 20.00 | 9.70 | 12.50 | 19.84 |
that:IN | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.50 | 20.00 |
Bush:NNP | 5.00 | 13.61 | 13.55 | 20.50 | 8.02 | 12.11 | 20.50 |
has:VBZ | 13.02 | 9.34 | 0.50 | 20.00 | 7.65 | 13.02 | 20.00 |
the:DT | 20.50 | 18.65 | 20.00 | 0.00 | 20.00 | 20.50 | 10.00 |
lead:NN | 8.02 | 13.11 | 10.68 | 20.00 | 0.00 | 8.02 | 19.02 |
Ohio:NNP | 12.11 | 14.84 | 14.84 | 20.50 | 8.02 | 0.00 | 20.50 |
.:. | 20.50 | 20.00 | 20.00 | 10.00 | 19.02 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -8.5000
Features matched: Factive.factivePassage: factive entails : surprising-JJ; NullPunisher.aux: does; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "surprising vs. hyp "." <-punct-- "have", which aligned to text "has"
Hand-tuned score: -1.0500
Threshold: -11.4590
Txt: It is not likely that Bush has the lead in Ohio.
Hyp: Bush does have the lead in Ohio . (unknown)
Bush NNP |
does VBZ |
have VB |
the DT |
lead NN |
Ohio NNP |
. . |
|
It:PRP | 12.50 | 15.00 | 15.00 | 20.00 | 12.00 | 12.50 | 20.00 |
is:VBZ | 14.84 | 9.34 | 7.80 | 20.00 | 9.39 | 14.84 | 20.00 |
not:RB | 15.46 | 19.96 | 19.96 | 20.00 | 14.96 | 15.46 | 20.00 |
likely:JJ | 12.46 | 9.43 | 11.96 | 20.00 | 10.90 | 12.46 | 19.92 |
that:IN | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.50 | 20.00 |
Bush:NNP | 5.00 | 13.61 | 13.55 | 20.50 | 8.02 | 12.11 | 20.50 |
has:VBZ | 13.02 | 9.34 | 0.50 | 20.00 | 7.65 | 13.02 | 20.00 |
the:DT | 20.50 | 18.65 | 20.00 | 0.00 | 20.00 | 20.50 | 10.00 |
lead:NN | 8.02 | 13.11 | 10.68 | 20.00 | 0.00 | 8.02 | 19.02 |
Ohio:NNP | 12.11 | 14.84 | 14.84 | 20.50 | 8.02 | 0.00 | 20.50 |
.:. | 20.50 | 20.00 | 20.00 | 10.00 | 19.02 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -8.5000
Features matched: Factive.unknownPassage: non factive text -- unknown: likely-JJ; NullPunisher.aux: does; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "likely vs. hyp "." <-punct-- "have", which aligned to text "has"
Hand-tuned score: -1.5500
Threshold: -11.4590
Txt: Kerry knew that Edwards would accept the nomination.
Hyp: Kerry did know whether Edwards would accept the nomination . (yes)
Kerry NNP |
did VBD |
know VBP |
whether IN |
Edwards NNP |
would MD |
accept VB |
the DT |
nomination NN |
. . |
|
Kerry:NNP | 0.00 | 15.46 | 15.46 | 20.50 | 9.07 | 20.46 | 15.46 | 20.50 | 10.46 | 20.50 |
knew:VBD | 15.46 | 4.04 | 0.50 | 20.00 | 15.50 | 19.96 | 5.35 | 20.00 | 14.92 | 17.19 |
that:IN | 20.50 | 20.00 | 20.00 | 10.00 | 20.50 | 20.00 | 20.00 | 20.00 | 20.00 | 20.00 |
Edwards:NNP | 9.07 | 15.50 | 15.50 | 20.50 | 0.00 | 20.46 | 15.50 | 20.50 | 10.50 | 20.50 |
would:MD | 20.46 | 18.57 | 19.96 | 20.00 | 20.46 | 0.00 | 19.96 | 10.00 | 19.96 | 10.00 |
accept:VB | 15.46 | 7.47 | 1.00 | 20.00 | 15.50 | 19.96 | 0.00 | 20.00 | 15.00 | 18.61 |
the:DT | 20.50 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 | 20.00 | 0.00 | 20.00 | 10.00 |
nomination:NN | 10.46 | 14.36 | 14.84 | 20.00 | 10.50 | 19.96 | 15.00 | 20.00 | 0.00 | 19.99 |
.:. | 20.50 | 17.99 | 17.93 | 20.00 | 20.50 | 10.00 | 18.61 | 10.00 | 19.99 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -7.5394
Features matched: NullPunisher.functionWord: whether; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "knew"
Hand-tuned score: -1.1000
Threshold: -11.4590
Txt: Tom knows that Naples is in Campania.
Hyp: Tom does know where Naples is . (yes)
Tom NNP |
does VBZ |
know VB |
where WRB |
Naples NNP |
is VBZ |
. . |
|
Tom:NNP | 0.00 | 10.17 | 15.00 | 19.96 | 9.84 | 14.34 | 20.00 |
knows:VBZ | 15.00 | 2.16 | 0.50 | 19.96 | 15.50 | 8.07 | 20.00 |
that:IN | 20.00 | 20.00 | 20.00 | 18.69 | 20.50 | 20.00 | 20.00 |
Naples:NNP | 9.84 | 14.84 | 15.50 | 20.46 | 0.00 | 14.84 | 20.50 |
is:VBZ | 14.34 | 9.34 | 8.07 | 19.96 | 14.84 | 0.00 | 20.00 |
Campania:NNP | 9.84 | 14.84 | 15.50 | 20.46 | 2.00 | 14.84 | 20.50 |
.:. | 20.00 | 20.00 | 17.93 | 10.00 | 20.50 | 20.00 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -11.5000
Features matched: Adjunct.addPosCxt: hyp added where[where-WRB]; Adjunct.dropPosCxt: text adjunct "Campania" of "is" dropped on aligned hyp word "is"; NullPunisher.aux: does; NullPunisher.other: where
Hand-tuned score: -0.5500
Threshold: -11.4590
Txt: We met in September during the feast.
Hyp: The feast did take_place in September . (yes)
The DT |
feast NN |
did VBD |
take_place NN |
September NNP |
. . |
|
We:PRP | 20.00 | 12.00 | 15.00 | 12.00 | 12.50 | 20.00 |
met:VBD | 20.00 | 10.15 | 5.11 | 13.51 | 15.50 | 19.15 |
September:NNP | 20.50 | 10.50 | 14.19 | 9.84 | 0.00 | 20.50 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 20.50 | 10.00 |
feast:NN | 20.00 | 0.00 | 9.07 | 8.28 | 10.50 | 20.00 |
.:. | 10.00 | 20.00 | 17.99 | 20.00 | 20.50 | 0.00 |
NO_WORD | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -17.1092
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 09/01/1000; NullPunisher.other: take_place; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "met"; Structure.relMismatch: text "feast" is prep_during of "met" while hyp "feast" is nsubj of "did" which aligned to text "met"
Hand-tuned score: -2.0000
Threshold: -11.4590
Txt: It is false that Bin Laden was seen in Tora Bora.
Hyp: Bin_Laden was seen in Tora Bora . (no)
Bin_Laden NNP |
was VBD |
seen VBN |
Tora_Bora NNP |
. . |
|
It:PRP | 12.00 | 15.00 | 15.00 | 12.50 | 20.00 |
is:VBZ | 14.34 | 0.50 | 7.74 | 15.46 | 20.00 |
false:JJ | 11.96 | 11.96 | 11.96 | 12.46 | 18.76 |
that:IN | 20.00 | 20.00 | 20.00 | 20.50 | 20.00 |
Bin_Laden:NNP | 0.50 | 14.84 | 14.84 | 14.96 | 20.50 |
was:VBD | 14.34 | 0.00 | 7.11 | 15.46 | 20.00 |
seen:VBN | 14.34 | 7.11 | 0.00 | 15.46 | 18.17 |
Tora_Bora:NNP | 10.46 | 15.46 | 15.46 | 0.00 | 20.50 |
.:. | 20.00 | 20.00 | 18.17 | 20.50 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.5000
Features matched: Factive.negativeStatement: non factive text : false-JJ; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "false vs. hyp "." <-punct-- "seen", which aligned to text "seen"
Hand-tuned score: -7.0000
Threshold: -11.4590
Txt: It follows that Bin Laden was in Tora Bora.
Hyp: Bin_Laden was in Tora Bora . (yes)
Bin_Laden NNP |
was VBD |
Tora_Bora NNP |
. . |
|
It:PRP | 12.00 | 15.00 | 12.50 | 20.00 |
follows:VBZ | 15.00 | 10.00 | 15.46 | 17.41 |
that:IN | 20.00 | 20.00 | 20.50 | 20.00 |
Bin_Laden:NNP | 0.50 | 14.84 | 14.96 | 20.50 |
was:VBD | 14.34 | 0.00 | 15.46 | 20.00 |
Tora_Bora:NNP | 10.46 | 15.46 | 0.00 | 20.50 |
.:. | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.5000
Features matched: Factive.factivePassage: factive entails : follows-VBZ; Location.mismatch: no clear info of matching: be(X, prep_in); Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "follows vs. hyp "." <-punct-- "was", which aligned to text "was"
Hand-tuned score: -3.0000
Threshold: -11.4590
Txt: It is likely that Bin Laden was in Tora Bora.
Hyp: Bin_Laden was in Tora Bora . (unknown)
Bin_Laden NNP |
was VBD |
Tora_Bora NNP |
. . |
|
It:PRP | 12.00 | 15.00 | 12.50 | 20.00 |
is:VBZ | 14.34 | 0.50 | 15.46 | 20.00 |
likely:JJ | 11.96 | 11.96 | 12.46 | 19.92 |
that:IN | 20.00 | 20.00 | 20.50 | 20.00 |
Bin_Laden:NNP | 0.50 | 14.84 | 14.96 | 20.50 |
was:VBD | 14.34 | 0.00 | 15.46 | 20.00 |
Tora_Bora:NNP | 10.46 | 15.46 | 0.00 | 20.50 |
.:. | 20.00 | 20.00 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.5000
Features matched: Factive.unknownPassage: non factive text -- unknown: likely-JJ; Location.mismatch: no clear info of matching: be(X, prep_in); Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "likely vs. hyp "." <-punct-- "was", which aligned to text "was"
Hand-tuned score: -3.5000
Threshold: -11.4590
Txt: Tony Hall left Amman on Sunday.
Hyp: Tony Hall was in Amman on Sunday . (yes)
Tony_Hall NNP |
was VBD |
Amman NNP |
Sunday NNP |
. . |
|
Tony_Hall:NNP | 0.00 | 15.17 | 14.67 | 14.96 | 20.50 |
left:VBD | 15.17 | 7.11 | 11.79 | 15.50 | 19.46 |
Amman:NNP | 14.67 | 11.83 | 0.00 | 15.00 | 20.50 |
Sunday:NNP | 14.96 | 15.50 | 15.00 | 0.00 | 20.50 |
.:. | 20.50 | 20.00 | 20.50 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -9.1114
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/1000; Location.mismatch: no clear info of matching: be(X, prep_in); RootEntailment.poorlyAlignedRoot: "was" aligned badly to "left"; Structure.relMismatch: text "Amman" is dobj of "left" while hyp "Amman" is prep_in of "was" which aligned to text "left"
Hand-tuned score: -3.0000
Threshold: -11.4590
Txt: Tony Hall left Amman on Sunday.
Hyp: Tony Hall was in Amman on Saturday . (unknown)
Tony_Hall NNP |
was VBD |
Amman NNP |
Saturday NNP |
. . |
|
Tony_Hall:NNP | 0.00 | 15.17 | 14.67 | 14.96 | 20.50 |
left:VBD | 15.17 | 7.11 | 11.79 | 15.50 | 19.46 |
Amman:NNP | 14.67 | 11.83 | 0.00 | 15.00 | 20.50 |
Sunday:NNP | 14.96 | 15.50 | 15.00 | 4.13 | 20.50 |
.:. | 20.50 | 20.00 | 20.50 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -13.2437
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/1000; Location.mismatch: no clear info of matching: be(X, prep_in); Numeric.mismatch: date Saturday != Sunday; RootEntailment.poorlyAlignedRoot: "was" aligned badly to "left"; Structure.relMismatch: text "Amman" is dobj of "left" while hyp "Amman" is prep_in of "was" which aligned to text "left"
Hand-tuned score: -9.0000
Threshold: -11.4590
Txt: Khan sold 10 centrifuges to North Korea.
Hyp: North_Korea did buy 10 centrifuges . (yes)
North_Korea NNP |
did VBD |
buy VB |
10 CD |
centrifuges NNS |
. . |
|
Khan:NNP | 9.52 | 15.50 | 15.50 | 25.00 | 8.53 | 20.50 |
sold:VBD | 15.00 | 7.69 | 6.51 | 20.00 | 14.23 | 19.42 |
10:CD | 19.84 | 19.19 | 20.03 | 0.00 | 20.50 | 19.16 |
centrifuges:NNS | 9.34 | 15.00 | 14.88 | 20.50 | 0.00 | 19.93 |
North_Korea:NNP | 0.50 | 14.52 | 15.50 | 24.34 | 9.84 | 20.50 |
.:. | 20.00 | 17.99 | 20.00 | 19.16 | 19.93 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -10.0110
Features matched: NullPunisher.aux: did; RootEntailment.poorlyAlignedRoot: "buy" aligned badly to "sold"; Structure.relMismatch: text "North_Korea" is prep_to of "sold" while hyp "North_Korea" is nsubj of "buy" which aligned to text "sold"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: The US invasion of Afghanistan prevented Al-Qaida from attacking Ryad in 2002.
Hyp: Al-Qaida did attack Ryad in 2002 . (no)
Al-Qaida NNP |
did VBD |
attack NN |
Ryad VBN |
2002 CD |
. . |
|
The:DT | 20.50 | 20.00 | 20.00 | 20.50 | 20.50 | 10.00 |
US:NNP | 10.00 | 15.50 | 10.50 | 14.96 | 24.96 | 20.50 |
invasion:NN | 10.50 | 12.69 | 5.06 | 15.46 | 20.46 | 20.00 |
Afghanistan:NNP | 10.00 | 15.50 | 10.50 | 14.96 | 24.96 | 20.50 |
prevented:VBD | 15.50 | 9.29 | 11.37 | 10.46 | 20.37 | 18.96 |
Al-Qaida:NNP | 0.50 | 15.00 | 10.00 | 15.46 | 20.46 | 20.00 |
from:IN | 20.50 | 20.00 | 20.00 | 20.50 | 20.50 | 20.00 |
attacking:VBG | 15.50 | 7.62 | 0.50 | 10.46 | 20.26 | 19.81 |
Ryad:NNP | 9.96 | 15.46 | 10.46 | 0.00 | 24.96 | 20.50 |
2002:CD | 24.96 | 20.46 | 20.44 | 24.96 | 0.00 | 20.50 |
.:. | 20.50 | 17.99 | 20.00 | 20.50 | 20.50 | 0.00 |
NO_WORD | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -18.2890
Features matched: Date.matchDatesByNormForm: hyp/txt matching, by normalized form: 01/01/2002; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "prevented"; Structure.relMismatch: text "Al-Qaida" is dobj of "prevented" while hyp "Al-Qaida" is nsubj of "did" which aligned to text "prevented"
Hand-tuned score: -1.0000
Threshold: -11.4590
Txt: The administration managed to track down the perpetrators.
Hyp: The administration did track_down the perpetrators . (yes)
The DT |
administration NN |
did VBD |
track_down VB |
the DT |
perpetrators NNS |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
administration:NN | 20.00 | 0.00 | 12.69 | 13.86 | 20.00 | 9.76 | 19.88 |
managed:VBD | 20.00 | 13.37 | 1.52 | 10.00 | 20.00 | 15.00 | 20.00 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 10.00 |
track_down:VB | 20.00 | 13.86 | 7.72 | 0.00 | 20.00 | 14.02 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
perpetrators:NNS | 20.00 | 9.76 | 14.73 | 14.02 | 20.00 | 0.00 | 19.30 |
.:. | 10.00 | 19.88 | 17.99 | 20.00 | 10.00 | 19.30 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -5.0000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "administration" <-nsubj-- "managed vs. hyp "administration" <-nsubj-- "track_down", which aligned to text "track_down" args have different parents but same relations: text "." <-punct-- "managed vs. hyp "." <-punct-- "track_down", which aligned to text "track_down"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: The administration didn't manage to track down the perpetrators.
Hyp: The administration did track_down the perpetrators . (no)
The DT |
administration NN |
did VBD |
track_down VB |
the DT |
perpetrators NNS |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
administration:NN | 20.00 | 0.00 | 12.69 | 13.86 | 20.00 | 9.76 | 19.88 |
did:VBD | 20.00 | 12.69 | 0.00 | 7.72 | 20.00 | 14.73 | 17.99 |
n't:RB | 20.00 | 14.96 | 13.27 | 19.96 | 20.00 | 13.39 | 17.90 |
manage:VB | 20.00 | 15.00 | 1.52 | 10.00 | 20.00 | 14.77 | 19.98 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 10.00 |
track_down:VB | 20.00 | 13.86 | 7.72 | 0.00 | 20.00 | 14.02 | 20.00 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
perpetrators:NNS | 20.00 | 9.76 | 14.73 | 14.02 | 20.00 | 0.00 | 19.30 |
.:. | 10.00 | 19.88 | 17.99 | 20.00 | 10.00 | 19.30 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -5.0000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "administration" <-nsubj-- "manage vs. hyp "administration" <-nsubj-- "track_down", which aligned to text "track_down" args have different parents but same relations: text "." <-punct-- "manage vs. hyp "." <-punct-- "track_down", which aligned to text "track_down"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: Bush didn't have the time to read the report.
Hyp: Bush did read the report . (no)
Bush NNP |
did VBD |
read VB |
the DT |
report NN |
. . |
|
Bush:NNP | 0.00 | 15.00 | 13.95 | 20.00 | 10.00 | 20.00 |
did:VBD | 15.00 | 0.00 | 6.81 | 20.00 | 12.69 | 17.99 |
n't:RB | 14.96 | 13.27 | 18.98 | 20.00 | 14.01 | 17.90 |
have:VB | 13.05 | 7.32 | 1.00 | 20.00 | 12.80 | 20.00 |
the:DT | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
time:NN | 10.00 | 11.26 | 12.32 | 20.00 | 6.89 | 17.52 |
to:TO | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 10.00 |
read:VB | 13.95 | 6.81 | 0.00 | 20.00 | 11.87 | 18.96 |
the:DT | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
report:NN | 10.00 | 12.69 | 11.87 | 20.00 | 0.00 | 19.87 |
.:. | 20.00 | 17.99 | 18.96 | 10.00 | 19.87 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -5.0000
Features matched: Factive.inNegatedEmbedding: embedded negative text; NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "Bush" <-nsubj-- "have vs. hyp "Bush" <-nsubj-- "read", which aligned to text "read" args have different parents but same relations: text "." <-punct-- "have vs. hyp "." <-punct-- "read", which aligned to text "read"
Hand-tuned score: -7.0500
Threshold: -11.4590
Txt: Bush had the time to read the report.
Hyp: Bush did read the report . (yes)
Bush NNP |
did VBD |
read VB |
the DT |
report NN |
. . |
|
Bush:NNP | 0.00 | 15.00 | 13.95 | 20.00 | 10.00 | 20.00 |
had:VBD | 13.05 | 7.32 | 5.95 | 20.00 | 12.80 | 20.00 |
the:DT | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
time:NN | 10.00 | 11.26 | 12.32 | 20.00 | 6.89 | 17.52 |
to:TO | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 10.00 |
read:VB | 13.95 | 6.81 | 0.00 | 20.00 | 11.87 | 18.96 |
the:DT | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
report:NN | 10.00 | 12.69 | 11.87 | 20.00 | 0.00 | 19.87 |
.:. | 20.00 | 17.99 | 18.96 | 10.00 | 19.87 | 0.00 |
NO_WORD | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -5.0000
Features matched: Factive.inPositiveEmbedding: embedded positive text; NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "Bush" <-nsubj-- "had vs. hyp "Bush" <-nsubj-- "read", which aligned to text "read" args have different parents but same relations: text "." <-punct-- "had vs. hyp "." <-punct-- "read", which aligned to text "read"
Hand-tuned score: -1.0500
Threshold: -11.4590
Txt: The president wasn't able to attend the meeting.
Hyp: The president did attend the meeting . (no)
The DT |
president NN |
did VBD |
attend VB |
the DT |
meeting NN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
president:NN | 20.00 | 0.00 | 15.00 | 14.16 | 20.00 | 8.35 | 20.00 |
was:VBD | 20.00 | 14.34 | 10.00 | 10.00 | 20.00 | 12.52 | 20.00 |
n't:RB | 20.00 | 14.96 | 13.27 | 18.46 | 20.00 | 14.96 | 17.90 |
able:JJ | 20.00 | 11.96 | 11.55 | 10.38 | 20.00 | 11.96 | 17.24 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 10.00 |
attend:VB | 20.00 | 14.16 | 8.17 | 0.00 | 20.00 | 11.65 | 19.67 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
meeting:NN | 20.00 | 8.35 | 12.69 | 11.65 | 20.00 | 0.00 | 19.92 |
.:. | 10.00 | 20.00 | 17.99 | 19.67 | 10.00 | 19.92 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -5.0000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "president" <-nsubj-- "able vs. hyp "president" <-nsubj-- "attend", which aligned to text "attend" args have different parents but same relations: text "." <-punct-- "able vs. hyp "." <-punct-- "attend", which aligned to text "attend"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: The president was able to attend the meeting.
Hyp: The president did attend the meeting . (yes)
The DT |
president NN |
did VBD |
attend VB |
the DT |
meeting NN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
president:NN | 20.00 | 0.00 | 15.00 | 14.16 | 20.00 | 8.35 | 20.00 |
was:VBD | 20.00 | 14.34 | 10.00 | 10.00 | 20.00 | 12.52 | 20.00 |
able:JJ | 20.00 | 11.96 | 11.55 | 10.38 | 20.00 | 11.96 | 17.24 |
to:TO | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 10.00 |
attend:VB | 20.00 | 14.16 | 8.17 | 0.00 | 20.00 | 11.65 | 19.67 |
the:DT | 0.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
meeting:NN | 20.00 | 8.35 | 12.69 | 11.65 | 20.00 | 0.00 | 19.92 |
.:. | 10.00 | 20.00 | 17.99 | 19.67 | 10.00 | 19.92 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -5.0000
Features matched: NullPunisher.aux: did; Structure.argsMismatch: args have different parents but same relations: text "president" <-nsubj-- "able vs. hyp "president" <-nsubj-- "attend", which aligned to text "attend" args have different parents but same relations: text "." <-punct-- "able vs. hyp "." <-punct-- "attend", which aligned to text "attend"
Hand-tuned score: -2.0500
Threshold: -11.4590
Txt: Many soldiers were killed in the ambush.
Hyp: All soldiers were killed in the ambush . (no)
All DT |
soldiers NNS |
were VBD |
killed VBN |
the DT |
ambush NN |
. . |
|
Many:JJ | 20.00 | 11.96 | 11.96 | 11.96 | 20.00 | 11.96 | 20.00 |
soldiers:NNS | 20.00 | 0.00 | 14.34 | 9.33 | 20.00 | 4.63 | 20.00 |
were:VBD | 20.00 | 14.34 | 0.00 | 8.33 | 20.00 | 15.00 | 20.00 |
killed:VBN | 20.00 | 9.33 | 8.33 | 0.00 | 20.00 | 9.69 | 20.00 |
the:DT | 10.00 | 20.00 | 20.00 | 20.00 | 0.00 | 20.00 | 10.00 |
ambush:NN | 20.00 | 4.63 | 15.00 | 9.69 | 20.00 | 0.00 | 20.00 |
.:. | 10.00 | 20.00 | 20.00 | 20.00 | 10.00 | 20.00 | 0.00 |
NO_WORD | 10.00 | 10.00 | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -10.0000
Features matched: Adjunct.dropPosCxt: text adjunct "Many" of "soldiers" dropped on aligned hyp word "soldiers"; NullPunisher.other: All; Quant.expand: [many,all]
Hand-tuned score: -6.5000
Threshold: -11.4590
Txt: The man had $20 in his pocket.
Hyp: The man did have $ 40 in his pocket . (no)
The DT |
man NN |
did VBD |
have VB |
$ $ |
40 CD |
his PRP$ |
pocket NN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.50 | 20.50 | 20.00 | 20.00 | 10.00 |
man:NN | 20.00 | 0.00 | 12.63 | 13.05 | 18.93 | 20.50 | 12.00 | 6.78 | 19.76 |
had:VBD | 20.00 | 13.05 | 7.32 | 0.50 | 20.50 | 20.50 | 15.00 | 13.95 | 20.00 |
$:$ | 10.50 | 18.93 | 20.50 | 20.50 | 0.00 | 20.00 | 20.50 | 17.92 | 9.91 |
20:CD | 20.50 | 20.50 | 19.19 | 20.50 | 20.00 | 0.69 | 20.50 | 19.19 | 19.23 |
his:PRP$ | 20.00 | 12.00 | 15.00 | 15.00 | 20.50 | 20.50 | 0.00 | 12.00 | 20.00 |
pocket:NN | 20.00 | 6.78 | 12.53 | 13.95 | 17.92 | 19.19 | 12.00 | 0.00 | 18.62 |
.:. | 10.00 | 19.76 | 17.99 | 20.00 | 9.91 | 18.57 | 20.00 | 18.62 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (INCORRECT)
Justification:
Alignment score: -2.1931
Features matched: NullPunisher.aux: did; Numeric.mismatch: MONEY mismatch: '$40.0' vs '$20.0'
Hand-tuned score: -5.0500
Threshold: -11.4590
Txt: The man had $20 in his pocket.
Hyp: The man did have $ 10 in his pocket . (yes)
The DT |
man NN |
did VBD |
have VB |
$ $ |
10 CD |
his PRP$ |
pocket NN |
. . |
|
The:DT | 0.00 | 20.00 | 20.00 | 20.00 | 10.50 | 20.50 | 20.00 | 20.00 | 10.00 |
man:NN | 20.00 | 0.00 | 12.63 | 13.05 | 18.93 | 20.50 | 12.00 | 6.78 | 19.76 |
had:VBD | 20.00 | 13.05 | 7.32 | 0.50 | 20.50 | 20.50 | 15.00 | 13.95 | 20.00 |
$:$ | 10.50 | 18.93 | 20.50 | 20.50 | 0.00 | 20.00 | 20.50 | 17.92 | 9.91 |
20:CD | 20.50 | 20.50 | 19.19 | 20.50 | 20.00 | 0.69 | 20.50 | 19.19 | 19.23 |
his:PRP$ | 20.00 | 12.00 | 15.00 | 15.00 | 20.50 | 20.50 | 0.00 | 12.00 | 20.00 |
pocket:NN | 20.00 | 6.78 | 12.53 | 13.95 | 17.92 | 19.19 | 12.00 | 0.00 | 18.62 |
.:. | 10.00 | 19.76 | 17.99 | 20.00 | 9.91 | 19.16 | 20.00 | 18.62 | 0.00 |
NO_WORD | 1.00 | 10.00 | 1.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 | 10.00 |
Response: yes (CORRECT)
Justification:
Alignment score: -2.1931
Features matched: NullPunisher.aux: did; Numeric.mismatch: MONEY mismatch: '$10.0' vs '$20.0'
Hand-tuned score: -5.0500
Threshold: -11.4590
java edu.stanford.nlp.rte.WordSimilarityGenerator -info /u/nlp/rte/data/byformat/align/stochastic/parc_dev.pipeline.align.xml -output /u/nlp/rte/data/byformat/wordsim/stochastic/parc_dev.pipeline.wordsim.html -lex.BasicWN off