Txt/Hyp term similarities

The rows are the txt words. The columns are hyp words.
Resource summary:
Acronym: AcronymLexicalResource
BasicWN: BasicWNLexicalResource
Country: CountryLexicalResource
Cyc: null
DekangLin: DekangLinLexicalResource
Google: null
InfoMap: InfoMapLexicalResource
NomBank: NomBankLexicalResource
Number: NumberLexicalResource
Ordinal: OrdinalLexicalResource
Preposition: PrepositionLexicalResource
Ravichandran: RavichandranLexicalResource
ResnikWN: ResnikWNLexicalResource
StringSim: StringSimLexicalResource



Inference ID: Cycorp-001

Txt: Sandy owns a Golden Retriever, Harley, with whom she has won a Dog World Award.

Hyp: Harley is a herding dog . (No.)

Harley
NNP
is
VBZ
a
DT
herding
JJ
dog
NN
.
.
Sandy:NNP   9.96 15.46 20.50 12.46 10.46 20.50
owns:VBZ 15.46 10.00 20.00 12.00 14.72 19.98
a:DT 20.50 20.00   0.00 20.00 20.00 10.00
Golden_Retriever:NNP 14.96 14.84 20.50 12.46   3.88 20.50
,:, 20.50 20.00 10.00 20.00 18.12   5.73
Harley:NNP   0.00 15.46 20.50 12.46 10.46 20.50
,:, 20.50 20.00 10.00 20.00 18.12   5.73
with:IN 20.50 20.00 18.45 20.00 20.00 20.00
she:PRP 12.50 15.00 20.00 15.00 12.00 20.00
has:VBZ 15.46   8.64 20.00 12.00 14.34 20.00
won:VBN 15.46 10.00 20.00 11.04 15.00 19.64
a:DT 20.50 20.00   0.00 20.00 20.00 10.00
Dog:NNP 14.96 12.84 20.50 12.50   0.50 20.50
World:NNP 14.96 14.84 20.50 10.63   9.45 20.50
Award:NNP 14.96 15.50 20.50 12.50 10.50 20.50
.:. 20.50 20.00 10.00 19.45 19.56   0.00
NO_WORD 10.00   1.00   1.00   9.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -15.5000
Features matched: Adjunct.addPosCxt: hyp added herding[herding-JJ]; Adjunct.dropPosCxt: text adjunct "won" of "Harley" dropped on aligned hyp word "Harley"; NullPunisher.aux: is; NullPunisher.other: herding; NullPunisher.article: a; Structure.argsMismatch: args have different parents but same relations: text "Harley" <-appos-- "Golden_Retriever vs. hyp "Harley" <-nsubj-- "dog", which aligned to text "Dog" args have different parents but same relations: text "." <-punct-- "owns vs. hyp "." <-punct-- "dog", which aligned to text "Dog" args have different parents, different relations: text "Harley" <-dep-- "with" vs. hyp "Harley" <-nsubj-- "dog", which aligned to text "Dog"
Hand-tuned score: -3.6500
Threshold: -11.4590


Inference ID: Cycorp-002

Txt: Many cellphones have built-in digital cameras.

Hyp: Some cellphones can be used to take pictures . (Yes.)

Some
DT
cellphones
NNS
can
MD
be
VB
used
VBN
to
TO
take
VB
pictures
NNS
.
.
Many:JJ 20.00 11.96 19.96 11.96 11.96 20.00 11.96 11.96 20.00
cellphones:NNS 20.00   0.00 17.12 14.34 15.00 20.00 15.00   8.03 20.00
have:VBP 20.00 13.95 17.32   7.80   6.55 20.00   1.83 12.32 20.00
built-in:JJ 20.00 11.96 19.96 11.96 11.96 20.00 11.96 11.96 20.00
digital_cameras:NNS 20.00   5.06 17.12 14.34 14.96 20.00 14.96   8.03 20.00
.:. 10.00 20.00 10.00 20.00 18.25 10.00 17.67 18.10   0.00
NO_WORD 10.00 10.00 10.00   1.00 10.00 10.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -51.4203
Features matched: Adjunct.dropPosCxt: text adjunct "built-in" of "digital_cameras" dropped on aligned hyp word "pictures"; Modal.yes: actual -> possible; NullPunisher.functionWord: to; NullPunisher.aux: be; NullPunisher.other: Some; NullPunisher.aux: can; Quant.contract: [many,some]; RootEntailment.poorlyAlignedRoot: "used" aligned badly to "have"; Structure.relMismatch: text "cellphones" is nsubj of "have" while hyp "cellphones" is nsubjpass of "used" which aligned to text "have"
Hand-tuned score: 0.3000
Threshold: -11.4590


Inference ID: Cycorp-003

Txt: One in four cellphones sold has a camera in it.

Hyp: Do most cell_phones have a lens . (No.)

Do
VB
most
JJS
cell_phones
NNS
have
VB
a
DT
lens
NN
.
.
One:CD 19.19 20.46 19.84 20.50 20.50 20.50 20.50
four:CD 19.19 20.46 19.84 20.50 20.50 20.50 19.35
cellphones:NNS 15.00 11.96   1.90 13.95 20.00   3.53 20.00
sold:VBN   7.69 11.96 12.80   5.68 20.00 13.35 19.42
has:VBZ   7.53 11.96 14.34   0.50 20.00 14.34 20.00
a:DT 20.00 20.00 20.00 20.00   0.00 20.00 10.00
camera:NN 15.00 11.96   6.77 13.95 20.00   3.53 18.65
it:PRP 15.00 15.00 12.00 15.00 20.00 12.00 20.00
.:. 20.00 20.00 20.00 20.00 10.00 20.00   0.00
NO_WORD 10.00   9.00 10.00 10.00   1.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -26.4626
Features matched: Adjunct.addPosCxt: hyp added most[most-JJS]; Adjunct.dropPosCxt: text adjunct "it" of "camera" dropped on aligned hyp word "lens"; Polarity.hypNegMarker: "most": JJS; NullPunisher.other: most; Quant.contract: [a,a]; RootEntailment.poorlyAlignedRoot: "Do" aligned badly to "has"
Hand-tuned score: -1.5000
Threshold: -11.4590


Inference ID: Cycorp-004

Txt: Three in four cellphones sold has a camera in it.

Hyp: Do most cell_phones have a lens . (Yes.)

Do
VB
most
JJS
cell_phones
NNS
have
VB
a
DT
lens
NN
.
.
Three:CD 19.19 20.46 19.84 20.50 20.50 20.50 20.50
four:CD 19.19 20.46 19.84 20.50 20.50 20.50 19.35
cellphones:NNS 15.00 11.96   1.90 13.95 20.00   3.53 20.00
sold:VBN   7.69 11.96 12.80   5.68 20.00 13.35 19.42
has:VBZ   7.53 11.96 14.34   0.50 20.00 14.34 20.00
a:DT 20.00 20.00 20.00 20.00   0.00 20.00 10.00
camera:NN 15.00 11.96   6.77 13.95 20.00   3.53 18.65
it:PRP 15.00 15.00 12.00 15.00 20.00 12.00 20.00
.:. 20.00 20.00 20.00 20.00 10.00 20.00   0.00
NO_WORD 10.00   9.00 10.00 10.00   1.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -26.4626
Features matched: Adjunct.addPosCxt: hyp added most[most-JJS]; Adjunct.dropPosCxt: text adjunct "it" of "camera" dropped on aligned hyp word "lens"; Polarity.hypNegMarker: "most": JJS; NullPunisher.other: most; Quant.contract: [a,a]; RootEntailment.poorlyAlignedRoot: "Do" aligned badly to "has"
Hand-tuned score: -1.5000
Threshold: -11.4590


Inference ID: Cycorp-005

Txt: Mr. Radley ordered a 16 ounce slab of slowly roasted Black Angus Prime Rib.

Hyp: Radley is a vegetarian . (No.)

Radley
NNP
is
VBZ
a
DT
vegetarian
NN
.
.
Mr._Radley:NNP   0.00 15.46 20.50 10.46 20.50
ordered:VBD 15.46   7.74 20.00 15.00 20.00
a:DT 20.50 20.00   0.00 20.00 10.00
16:CD 24.96 20.50 20.50 19.80 19.82
ounce:NN 10.46 14.34 20.00   8.11 19.86
slab:NN 10.46 14.34 20.00   8.03 20.00
slowly:RB 15.46 19.96 20.00 14.96 18.14
roasted:JJ 12.46   9.34 20.00   7.83 20.00
Black_Angus_Prime_Rib:NNP 14.96 14.17 20.50   9.52 20.50
.:. 20.50 20.00 10.00 20.00   0.00
NO_WORD 10.00   1.00   1.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -13.0325
Features matched: Adjunct.dropPosCxt: text adjunct "Black_Angus_Prime_Rib" of "slab" dropped on aligned hyp word "vegetarian"; NullPunisher.aux: is; Quant.contract: [a,a]; RootEntailment.poorlyAlignedRoot: "vegetarian" aligned badly to "slab"; Structure.argsMismatch: args have different parents but same relations: text "Mr._Radley" <-nsubj-- "ordered vs. hyp "Radley" <-nsubj-- "vegetarian", which aligned to text "slab" args have different parents but same relations: text "." <-punct-- "ordered vs. hyp "." <-punct-- "vegetarian", which aligned to text "slab"
Hand-tuned score: -2.5500
Threshold: -11.4590


Inference ID: Cycorp-006

Txt: Sue ran down to McDonald's and got a hamburger happy meal with a large Diet Coke.

Hyp: Sue did get a cup . (Yes.)

Sue
NNP
did
VBD
get
VB
a
DT
cup
NN
.
.
Sue:NNP   0.00 15.00 12.65 20.00   7.65 20.00
ran_down:VBD 13.82   7.45   3.85 20.00 12.62 20.00
McDonald:NNP 10.46 15.46 15.46 20.50 10.46 20.50
got:VBD 12.65   5.62   0.50 20.00 12.62 17.75
a:DT 20.00 20.00 20.00   0.00 20.00 10.00
hamburger:RB 14.34 18.41 18.31 20.00 10.84 20.00
happy:JJ 11.96 11.96   6.05 20.00 11.42 17.14
meal:NN   9.34 13.69 12.37 20.00   5.84 19.61
a:DT 20.00 20.00 20.00   0.00 20.00 10.00
large:JJ 12.00   9.53 12.00 20.00   8.55 18.45
Diet_Coke:NN   9.54 15.46 13.79 20.50   7.82 20.50
.:. 20.00 17.99 17.78 10.00 20.00   0.00
NO_WORD 10.00   1.00 10.00   1.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -11.3413
Features matched: Adjunct.dropPosCxt: text adjunct "happy" of "meal" dropped on aligned hyp word "cup"; NullPunisher.aux: did; Quant.contract: [a,a]; Structure.argsMismatch: args have different parents but same relations: text "Sue" <-nsubj-- "ran_down vs. hyp "Sue" <-nsubj-- "get", which aligned to text "got" args have different parents but same relations: text "." <-punct-- "ran_down vs. hyp "." <-punct-- "get", which aligned to text "got"
Hand-tuned score: -0.5500
Threshold: -11.4590


Inference ID: Cycorp-007

Txt: Angela Drake will be moving to California with her husband, where she has accepted a full-time position with the San Diego Public Library.

Hyp: Angela Drake does live in Los_Angeles . (No.)

Angela_Drake
NNP
does
VBZ
live
VB
Los_Angeles
NNP
.
.
Angela_Drake:NNP   0.00 13.23 15.46 10.46 20.50
will:MD 20.46 20.00 20.00 19.96 10.00
be:VB 15.17   9.34   1.00 14.34 20.00
moving:VBG 15.46 10.00   4.03 14.96 17.38
California:NNP 14.67 14.84 15.50   2.50 20.50
her:PRP$ 12.50 15.00 15.00 12.00 20.00
husband:NN   9.52 13.11 13.53   9.34 19.33
,:, 20.50 19.26 17.82 20.00   5.73
where:WRB 20.46 19.96 19.96 19.96 10.00
she:PRP 12.50 15.00 15.00 12.00 20.00
has:VBZ 15.17   9.34 10.00 12.52 20.00
accepted:VBN 15.46 10.00   8.07 14.96 17.53
a:DT 20.50 20.00 20.00 20.00 10.00
full-time:JJ 12.46 11.96 10.88 11.96 17.39
position:NN 10.17 14.34 15.00   6.03 18.83
the:DT 20.50 18.65 20.00 20.00 10.00
San_Diego_Public_Library:NNP 14.47 14.41 15.46 10.46 20.50
.:. 20.50 20.00 18.97 20.00   0.00
NO_WORD 10.00   1.00 10.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -12.8582
Features matched: Adjunct.dropPosCxt: text adjunct "husband" of "moving" dropped on aligned hyp word "live"; NullPunisher.aux: does; RootEntailment.poorlyAlignedRoot: "live" aligned badly to "moving"; Structure.relMismatch: text "California" is prep_to of "moving" while hyp "Los_Angeles" is prep_in of "live" which aligned to text "moving"
Hand-tuned score: -1.5500
Threshold: -11.4590


Inference ID: Cycorp-008

Txt: Ambassador Richard C. Holbrooke will visit Paris, France from Saturday, April 22 until Tuesday, April 25.

Hyp: Ambassador Holbrooke will visit France in April . (Yes.)

Ambassador
NNP
Holbrooke
NNP
will
MD
visit
VB
France
NNP
April
NNP
.
.
Ambassador:NNP   0.00   9.29 20.00 15.00   8.55 10.50 20.00
Richard_C._Holbrooke:NNP 10.46   0.00 20.46 15.46 14.96 14.96 20.50
will:MD 20.00 20.46   0.00 20.00 20.50 19.19 10.00
visit:VB 15.00 15.46 20.00   0.00 15.50 15.50 20.00
Paris:NNP   9.84 14.96 20.50 13.63   2.00 15.00 20.50
,:, 20.50 25.00 10.50 20.50 25.00 20.00   6.23
France:NNP   8.55 14.96 20.50 15.50   0.00 15.00 20.50
Saturday:NNP 10.50 14.96 19.19 15.50 15.00   7.23 20.50
,:, 20.50 25.00 10.50 20.50 25.00 20.00   6.23
April:NNP 10.50 14.96 19.19 15.50 15.00   0.00 20.50
22:CD 20.50 24.96 19.19 20.50 25.00 17.84 19.32
Tuesday:NNP 10.50 14.96 19.19 15.50 15.00   7.23 20.50
,:, 20.50 25.00 10.50 20.50 25.00 20.00   6.23
April:NNP 10.50 14.96 19.19 15.50 15.00   0.00 20.50
25:CD 20.50 24.96 19.19 20.50 25.00 17.84 19.52
.:. 20.00 20.50 10.00 20.00 20.50 20.50   0.00
NO_WORD 10.00 10.00 10.00 10.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -4.0000
Features matched: Adjunct.dropPosCxt: text adjunct "25" of "April" dropped on aligned hyp word "April"; Date.matchDatesByGraph: hyp/txt matching, by graph: April and children; Structure.parentsMismatch: args have different parents, different relations: text "France" <-appos-- "Paris" vs. hyp "France" <-dobj-- "visit", which aligned to text "visit"
Hand-tuned score: -0.5000
Threshold: -11.4590


Inference ID: Cycorp-009

Txt: A full-time administrative assistant, Janet Smith lives close to Long Beach, where she's worked for the past 12 years.

Hyp: Janet Smith does live in Long_Beach . (No.)

Janet_Smith
NNP
does
VBZ
live
VB
Long_Beach
NNP
.
.
A:DT 20.50 20.00 20.00 20.00 10.00
full-time:JJ 12.46 11.96 10.88 11.96 17.39
administrative:JJ 12.46 10.80 11.96 11.96 19.85
assistant:NN   8.61 13.11 15.00   9.34 20.00
,:, 20.50 19.26 17.82 20.00   5.73
Janet_Smith:NNP   0.00 14.55 15.46   9.97 20.50
lives:VBZ 14.52   8.11   0.50 13.62 18.56
Long_Beach:NNP 14.47 14.84 15.50   0.50 20.50
,:, 20.50 19.26 17.82 20.00   5.73
where:WRB 20.46 19.96 19.96 19.96 10.00
she:PRP 12.50 15.00 15.00 12.00 20.00
's:VBZ 15.17   6.09   9.76 13.92 18.25
worked:VBN 14.97   8.95   8.07 12.52 18.80
the:DT 20.50 18.65 20.00 20.00 10.00
past:JJ 12.46 10.13 12.00 10.62 19.32
12:CD 24.96 20.50 19.17 19.42 19.69
years:NNS 10.46 15.00 14.82   6.52 19.49
.:. 20.50 20.00 18.97 20.00   0.00
NO_WORD 10.00   1.00 10.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -5.0000
Features matched: NullPunisher.aux: does; Structure.argsMismatch: args have different parents but same relations: text "Janet_Smith" <-appos-- "assistant vs. hyp "Janet_Smith" <-nsubj-- "live", which aligned to text "lives" text "Long_Beach" is prep_close_to of "lives" while hyp "Long_Beach" is prep_in of "live" which aligned to text "lives"
Hand-tuned score: -2.0500
Threshold: -11.4590


Inference ID: Cycorp-010

Txt: Bob Appleton, 33, lives in Sacramento but commutes to Davis in his silver Honda CRV.

Hyp: Appleton does have a California Driver 's license . (Yes.)

Appleton
NNP
does
VBZ
have
VB
a
DT
California_Driver
NNP
license
NN
.
.
Bob_Appleton:NNP   5.00 14.55 14.31 20.50 13.17   9.68 20.50
,:, 20.50 19.26 20.00 10.00 20.50 19.79   5.73
33:CD 24.96 20.46 20.46 20.50 24.96 20.46 18.52
,:, 20.50 19.26 20.00 10.00 20.50 19.79   5.73
lives:VBZ 13.55   8.11   8.05 20.00 14.42 12.44 18.56
Sacramento:NNP 10.69 14.84 14.84 20.50 13.17 10.50 20.50
commutes:NNP 10.50 14.05 12.32 20.00 10.46 10.00 20.00
Davis:NNP 13.05 13.61 13.55 20.50 12.04 10.50 20.50
his:PRP$ 12.50 15.00 15.00 20.00 12.50 12.00 20.00
silver:JJ 11.45 10.95   9.61 20.00 11.42   9.85 18.95
Honda_CRV:NN   9.96 15.46 15.46 20.50   9.96 10.46 20.50
.:. 20.50 20.00 20.00 10.00 20.50 19.98   0.00
NO_WORD 10.00   1.00 10.00   1.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -35.0496
Features matched: Adjunct.dropPosCxt: text adjunct "Davis" of "lives" dropped on aligned hyp word "have"; NullPunisher.article: a; NullPunisher.aux: does; NullPunisher.other: California_Driver; NullPunisher.other: license; RootEntailment.poorlyAlignedRoot: "have" aligned badly to "lives"
Hand-tuned score: -2.6500
Threshold: -11.4590


Inference ID: Cycorp-011

Txt: When they remodeled their house, the Kirchners transformed the original kitchen into a game room with dark cherry laminate flooring and cabinets.

Hyp: Does the Krichners ' kitchen have cherry cabinets ? (Unknown.)

Does
RB
the
DT
Krichners
NNPS
kitchen
NN
have
VBP
cherry
JJ
cabinets
NNS
?
.
When:WRB 19.96 10.00 20.46 19.96 19.96 19.96 19.96 10.00
they:PRP 20.00 15.71 12.50 12.00 15.00 15.00 12.00 20.00
remodeled:VBD 20.00 20.00 15.46 11.05   7.62   9.51 11.30 20.00
their:PRP$ 20.00 20.00 12.50 12.00 15.00 15.00 12.00 20.00
house:NN 11.69 20.00 10.46   6.19 13.95 10.29   6.66 20.00
,:, 20.00 10.00 20.50 18.54 20.00 17.15 18.85 10.00
the:DT 20.00   0.00 20.50 20.00 20.00 20.00 20.00 10.00
Kirchners:NNPS 13.61 20.50   9.44   9.45 13.55 10.61   9.45 20.50
transformed:VBD 20.00 20.00 15.46 15.00   7.61 12.00 15.00 19.73
the:DT 20.00   0.00 20.50 20.00 20.00 20.00 20.00 10.00
original:JJ 10.95 20.00 12.46 10.03 10.95   8.95 10.03 19.83
kitchen:NN 13.95 20.00 10.46   0.00 13.95   7.60   3.12 19.98
a:DT 20.00 10.00 20.50 20.00 20.00 20.00 20.00 10.00
game_room:NN 12.88 20.00 10.46   5.46 13.95   9.27   5.61 20.00
dark:JJ 11.34 20.00 12.46   6.73 11.34   5.26   8.72 20.00
cherry:JJ 10.11 20.00 12.46   7.60 10.11   0.00   7.97 19.72
laminate:JJ 10.95 20.00 12.46   8.72   9.62   6.18   7.69 18.60
flooring:NNS 13.95 20.00 10.46   5.75 13.95   8.75   5.08 20.00
cabinets:NNS 10.85 20.00 10.46   3.12 13.95   7.97   0.00 19.54
.:. 20.00 10.00 20.50 18.73 20.00 19.85 19.19 10.00
NO_WORD   9.00   1.00 10.00 10.00 10.00   9.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -43.6142
Features matched: Adjunct.addPosCxt: hyp added Does[Does-RB]; Adjunct.dropPosCxt: text adjunct "flooring" of "transformed" dropped on aligned hyp word "have"; NullPunisher.other: Does; NullPunisher.other: ?; NullPunisher.other: Krichners; NullPunisher.article: the; RootEntailment.poorlyAlignedRoot: "have" aligned badly to "transformed"; Structure.relMismatch: text "kitchen" is dobj of "transformed" while hyp "kitchen" is nsubj of "have" which aligned to text "transformed" text "cabinets" is prep_with of "transformed" while hyp "cabinets" is dobj of "have" which aligned to text "transformed"
Hand-tuned score: -5.6000
Threshold: -11.4590


Inference ID: Cycorp-012

Txt: Mark Jacobs, who lives in Edmonds and works in Seattle, spends 2 hours a day commuting.

Hyp: Jacobs does commute to work during rush_hour . (Yes.)

Jacobs
NNP
does
VBZ
commute
NN
to
TO
work
VB
rush_hour
NN
.
.
Mark_Jacobs:NNS   0.00 14.55   9.16 20.50 13.23   7.50 20.50
,:, 20.50 19.26 20.00 10.00 19.61 20.00   5.73
who:WP 12.50 15.00 12.00 20.00 15.00 12.00 20.00
lives:VBZ 13.55   8.11 10.16 20.00   6.27 12.82 18.56
Edmonds:NNP 14.96 15.46 10.46 20.50 15.46 10.46 20.50
works:VBZ 14.45   8.42 13.82 20.00   0.50 14.18 19.16
Seattle:NNP 14.34 14.84 10.50 20.50 10.96 10.17 20.50
,:, 20.50 19.26 20.00 10.00 19.61 20.00   5.73
spends:VBZ 15.50   8.12 11.68 20.00   7.78 15.00 20.00
2:CD 25.00 20.50 20.50 20.50 20.41 19.42 18.58
hours:NNS 10.50 15.00   6.02 20.00 11.60   5.00 19.95
a:DT 20.50 20.00 20.00 10.00 20.00 20.00 10.00
day:NN   4.79 13.11   7.09 20.00 12.57   8.01 18.14
commuting:VBG 15.50 10.00   0.50 20.00   3.90 13.04 20.00
.:. 20.50 20.00 19.75 10.00 18.57 20.00   0.00
NO_WORD 10.00 10.00 10.00 10.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -30.1176
Features matched: Adjunct.dropPosCxt: text adjunct "2" of "hours" dropped on aligned hyp word "rush_hour"; NullPunisher.functionWord: to; RootEntailment.poorlyAlignedRoot: "does" aligned badly to "spends"; Structure.parentsMismatch: args have different parents, different relations: text "commuting" <-partmod-- "hours" vs. hyp "commute" <-dobj-- "does", which aligned to text "spends" args have different parents, different relations: text "works" <-rcmod-- "Mark_Jacobs" vs. hyp "work" <-xcomp-- "does", which aligned to text "spends"
Hand-tuned score: -3.6000
Threshold: -11.4590


Inference ID: Cycorp-013

Txt: Terry Parks married Robert Paulson in 1979.

Hyp: Terry Parks is a man . (No.)

Terry_Parks
NNS
is
VBZ
a
DT
man
NN
.
.
Terry_Parks:NNS   0.00 15.17 20.50   9.52 20.50
married:VBD 15.46   8.07 20.00 10.61 19.71
Robert_Paulson:NNP   9.02 15.17 20.50   9.52 20.50
1979:CD 24.96 20.46 20.50 18.79 19.57
.:. 20.50 20.00 10.00 19.76   0.00
NO_WORD 10.00   1.00   1.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -12.6122
Features matched: NullPunisher.aux: is; NullPunisher.article: a; RootEntailment.poorlyAlignedRoot: "man" aligned badly to "married"
Hand-tuned score: -1.1500
Threshold: -11.4590


Inference ID: Cycorp-014

Txt: The Paulsons celebrated their 25th anniversary on June 14, 2004.

Hyp: The Paulsons did get_married on Flag_Day . (MULTIPLE ANSWERS)

The
DT
Paulsons
NNPS
did
VBD
get_married
VBN
Flag_Day
NNP
.
.
The:DT   0.00 20.50 20.00 20.00 20.00 10.00
Paulsons:NNPS 20.50   0.00 15.46 15.46 10.46 20.50
celebrated:VBD 20.00 15.46   9.33 10.00 15.00 20.00
their:PRP$ 20.00 12.50 15.00 15.00 12.00 20.00
25th:JJ 20.00 12.46 11.52 11.96 11.96 20.00
anniversary:NN 20.00 10.46 13.69 15.00   4.16 20.00
June_14:NNP 20.50 14.96 14.19 15.50   0.50 20.50
,:, 10.50 25.00 20.30 20.50 20.50   6.23
2004:CD 20.50 24.96 20.46 20.46 20.46 20.50
.:. 10.00 20.50 17.99 20.00 20.00   0.00
NO_WORD   1.00 10.00   1.00 10.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -11.8094
Features matched: Adjunct.dropPosCxt: text adjunct "2004" of "June_14" dropped on aligned hyp word "Flag_Day"; NullPunisher.aux: did; RootEntailment.poorlyAlignedRoot: "get_married" aligned badly to "celebrated"
Hand-tuned score: -0.5500
Threshold: -11.4590


Inference ID: Cycorp-015

Txt: The Island Nut Sampler includes an 8 ounce box of milk chocolate covered macadamia nuts and an 8 ounce box of white chocolate covered macadamia nuts.

Hyp: It does include a pound of macadamia nuts . (Yes.)

It
PRP
does
VBZ
include
VB
a
DT
pound
NN
macadamia
NN
nuts
NNS
.
.
The:DT 20.00 20.00 20.00 10.00 20.00 20.00 20.00 10.00
Island:NNP 12.50 14.45 15.50 20.50   9.45   9.45   9.45 20.50
Nut:NNP 12.50 13.61 15.50 20.50   8.34   8.61   0.81 20.50
Sampler:NNP 12.50 13.61 15.50 20.50   8.53   8.61   8.53 20.50
includes:VBZ 15.00   9.55   0.50 20.00 12.61 14.87 15.00 19.56
an:DT 20.00 17.89 20.00   8.73 20.00 20.00 20.00 10.00
8:CD 20.50 20.50 20.50 20.50 16.96 20.50 18.34 19.96
ounce:NN 12.00 10.17 15.00 20.00   0.94   8.11   7.84 19.86
box:NN 12.00 13.08 12.42 20.00   3.45   4.40   7.81 19.82
milk_chocolate:NN 12.00 14.34 12.87 20.00   8.81   8.53   8.44 20.00
covered:VBN 15.00   8.49   5.64 20.00 12.45 13.95 11.46 19.33
macadamia:NN 12.00 13.11 13.91 20.00   8.11   0.00   5.49 19.94
nuts:NNS 12.00 13.11 15.00 20.00   7.07   5.49   0.00 19.80
an:DT 20.00 17.89 20.00   8.73 20.00 20.00 20.00 10.00
8:CD 20.50 20.50 20.50 20.50 16.96 20.50 18.34 19.96
ounce:NN 12.00 10.17 15.00 20.00   0.94   8.11   7.84 19.86
box:NN 12.00 13.08 12.42 20.00   3.45   4.40   7.81 19.82
white_chocolate:NN 12.00 14.05 13.81 20.00   7.15   9.05   8.44 20.00
covered:VBD 15.00   8.49   5.64 20.00 12.45 13.95 11.46 19.33
macadamia:NN 12.00 13.11 13.91 20.00   8.11   0.00   5.49 19.94
nuts:NNS 12.00 13.11 15.00 20.00   7.07   5.49   0.00 19.80
.:. 20.00 20.00 19.86 10.00 19.64 19.94 19.80   0.00
NO_WORD 10.00   1.00 10.00   1.00 10.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -17.4408
Features matched: NullPunisher.aux: does; NullPunisher.other: It; NullPunisher.article: a; Structure.parentsMismatch: args have different parents, different relations: text "ounce" <-nn-- "box" vs. hyp "pound" <-dobj-- "include", which aligned to text "includes"
Hand-tuned score: -3.1500
Threshold: -11.4590


Inference ID: Cycorp-016

Txt: Nanolab says it can't stay profitable if the demand for nanotubes decreases.

Hyp: Nanolab does manufacture nanotubes . (MULTIPLE ANSWERS)

Nanolab
NNP
does
VBZ
manufacture
NN
nanotubes
NNS
.
.
Nanolab:NNP   0.00 14.96   9.96   9.96 20.00
says:VBZ 14.96   9.34 14.82 15.00 18.68
it:PRP 12.00 15.00 12.00 12.00 20.00
ca:MD 19.96 16.22 19.83 15.05   9.11
n't:RB 14.96 17.14 13.59 14.96 17.90
stay:VB 14.96   8.33 13.35 14.34 18.79
profitable:JJ 11.96 11.96   9.71 11.96 19.77
if:IN 20.00 16.87 20.00 20.00 20.00
the:DT 20.00 18.65 20.00 20.00 10.00
demand:NN   9.96 15.00   7.10 10.00 20.00
nanotubes:NNS   9.96 14.34 10.00   0.00 20.00
decreases:VBZ 14.96 10.00 12.69 15.00 19.25
.:. 20.00 20.00 19.10 20.00   0.00
NO_WORD 10.00 10.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -20.4384
Features matched: RootEntailment.poorlyAlignedRoot: "does" aligned badly to "says"; Structure.parentsMismatch: args have different parents, different relations: text "nanotubes" <-prep_for-- "demand" vs. hyp "nanotubes" <-dobj-- "does", which aligned to text "says"
Hand-tuned score: -4.0000
Threshold: -11.4590


Inference ID: Cycorp-017

Txt: The Swedish Embassy in Bangkok will be closed April 13-17 during the Songkran Festival.

Hyp: The Songkran Festival is a Swedish holiday . (Unknown.)

The
DT
Songkran_Festival
NNP
is
VBZ
a
DT
Swedish
JJ
holiday
NN
.
.
The:DT   0.00 20.50 20.00 10.00 20.50 20.00 10.00
Swedish:NNP 20.50 14.34 15.50 20.50   0.00   9.19 20.50
Embassy:NNP 20.50 14.96 14.84 20.50 12.00 10.50 20.50
Bangkok:NNP 20.50 14.96 14.84 20.50 17.00 10.50 20.50
will:MD 10.00 19.84 20.00 10.00 18.35 18.69 10.00
be:VB 20.00 15.46   0.31 20.00 12.50 15.00 20.00
closed:VBN 20.00 14.42   8.07 20.00 10.35 12.84 19.49
April:NNP 20.50 13.62 15.50 20.50 15.69   7.73 20.50
13-17:CD 20.50 24.96 20.46 20.50 24.96 20.24 19.37
the:DT   0.00 20.50 20.00 10.00 20.50 20.00 10.00
Songkran_Festival:NNP 20.50   0.00 15.46 20.50 16.34   9.12 20.50
.:. 10.00 20.50 20.00 10.00 20.50 19.99   0.00
NO_WORD   1.00 10.00   1.00   1.00   9.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -15.7318
Features matched: Adjunct.dropPosCxt: text adjunct "13-17" of "April" dropped on aligned hyp word "holiday"; NullPunisher.aux: is; NullPunisher.article: a; RootEntailment.poorlyAlignedRoot: "holiday" aligned badly to "April"; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "closed vs. hyp "." <-punct-- "holiday", which aligned to text "April" args have different parents, different relations: text "Songkran_Festival" <-prep_during-- "closed" vs. hyp "Songkran_Festival" <-nsubj-- "holiday", which aligned to text "April" args have different parents, different relations: text "Swedish" <-nn-- "Embassy" vs. hyp "Swedish" <-amod-- "holiday", which aligned to text "April" noun args have different parents but same relations: "Swedish": "Embassy" vs. "holiday"
Hand-tuned score: -3.6500
Threshold: -11.4590


Inference ID: Cycorp-018

Txt: The Nut Sampler set includes two 8 ounce boxes of chocolate covered nuts.

Hyp: This set does contain milk_chocolate covered nuts . (Unknown.)

This
DT
set
NN
does
VBZ
contain
VB
milk_chocolate
JJ
covered
VBN
nuts
NNS
.
.
The:DT 10.00 20.00 20.00 20.00 20.00 20.00 20.00 10.00
Nut_Sampler:NNP 20.50   5.65 14.55 15.46 10.94 13.73   5.65 20.50
set:NN 20.00   0.00 12.81 12.79 10.81   6.83   0.31 18.94
includes:VBZ 20.00 11.46   9.55   6.26   9.87   5.64 15.00 19.56
two:CD 20.50 18.34 20.50 19.56 19.84 19.92 18.34 19.42
8:CD 20.50 18.34 20.50 20.17 19.84 19.42 18.34 19.96
ounce:NN 20.00   7.84 10.17 14.37 11.34 13.95   7.84 19.86
boxes:NNS 20.00   7.12 13.11 12.66 10.76   9.85   7.84 18.97
chocolate:NN 20.00   8.69 14.34 14.77   2.00 11.75   3.08 19.54
covered:VBN 20.00   6.83   8.49   4.58 10.81   0.00 11.46 19.33
nuts:NNS 20.00   0.31 13.11 15.00 10.44 11.46   0.00 19.80
.:. 10.00 18.94 20.00 18.50 20.00 19.33 19.80   0.00
NO_WORD 10.00 10.00   1.00 10.00   9.00 10.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -23.2614
Features matched: Adjunct.dropPosCxt: text adjunct "Nut_Sampler" of "set" dropped on aligned hyp word "set"; NullPunisher.aux: does; NullPunisher.other: This; RootEntailment.poorlyAlignedRoot: "contain" aligned badly to "includes"; Structure.parentsMismatch: args have different parents, different relations: text "nuts" <-prep_of-- "boxes" vs. hyp "nuts" <-dobj-- "contain", which aligned to text "includes"
Hand-tuned score: -4.5500
Threshold: -11.4590


Inference ID: Cycorp-019

Txt: The Mini Mac was introduced by Apple CEO Steve Jobs at his keynote address on January 11.

Hyp: Apple Computer did release a new Macintosh in January . (Yes.)

Apple_Computer
NNP
did
VBD
release
VB
a
DT
new
JJ
Macintosh
NNP
January
NNP
.
.
The:DT 20.50 20.00 20.00 10.00 20.00 20.50 20.50 10.00
Mini_Mac:NNP   9.02 15.46 13.47 20.50 12.46   5.42 14.96 20.50
was:VBD 15.17 10.00   9.34 20.00 11.96 14.84 15.50 20.00
introduced:VBN 15.46   6.26   6.87 20.00 10.51 15.50 15.50 20.00
Apple:NNP   0.00 15.50 14.45 20.50 12.46   8.95 15.00 20.50
CEO:NNP   9.52 15.00 13.95 20.00 11.96   9.45 10.50 20.00
Steve_Jobs:NNP 14.02 14.34 13.89 20.50 12.46 14.02 14.34 20.50
his:PRP$ 12.50 15.00 15.00 20.00 15.00 12.50 12.50 20.00
keynote_address:NN 10.17 13.38 13.35 20.00 11.96 10.17   9.84 20.00
January:NNP 14.96 14.19 14.19 20.50 12.46 15.00   0.00 20.50
11:CD 24.96 19.19 19.19 20.50 20.30 25.00 17.84 19.37
.:. 20.50 17.99 19.68 10.00 20.00 20.50 20.50   0.00
NO_WORD 10.00   1.00 10.00   1.00   9.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -26.2923
Features matched: Adjunct.addPosCxt: hyp added new[new-JJ]; Adjunct.dropPosCxt: text adjunct "11" of "January" dropped on aligned hyp word "January"; Date.matchDatesByGraph: hyp/txt matching, by graph: January and children; NullPunisher.article: a; NullPunisher.other: new; NullPunisher.aux: did; Quant.contract: [the,a]; RootEntailment.poorlyAlignedRoot: "release" aligned badly to "introduced"; Structure.relMismatch: text "January" is prep_on of "introduced" while hyp "January" is prep_in of "release" which aligned to text "introduced"
Hand-tuned score: -1.6500
Threshold: -11.4590


Inference ID: Cycorp-020

Txt: The Donald criticized President Bush over his decision to go to war with Iraq.

Hyp: Trump does support W 's decision to go_to_war . (No.)

Trump
NNP
does
VBZ
support
VB
W
NNP
decision
NN
go_to_war
NN
.
.
The:DT 20.50 20.00 20.00 20.00 20.00 20.00 10.00
Donald:NNP 14.96 15.46 15.46 10.46 10.46 10.46 20.50
criticized:VBD 15.50 10.00   6.01 15.00 13.36 14.96 19.96
President_Bush:NNP   9.45 13.11 13.51   9.34   9.18   8.86 20.00
his:PRP$ 12.50 15.00 15.00 12.00 12.00 12.00 20.00
decision:NN 10.50 14.46 12.38   8.69   0.00   8.84 18.75
to:TO 20.50 17.95 20.00 20.00 20.00 20.00 10.00
go_to_go_to_war:VB 11.79   9.67   7.80 13.92 13.84   5.00 20.00
Iraq:NNP 14.34 14.84 14.84   9.84 10.50 10.17 20.50
.:. 20.50 20.00 18.74 20.00 18.75 20.00   0.00
NO_WORD 10.00   1.00 10.00 10.00 10.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -36.0073
Features matched: Adjunct.dropPosCxt: text adjunct "Iraq" of "go_to_go_to_war" dropped on aligned hyp word "go_to_war"; NullPunisher.other: Trump; NullPunisher.other: W; NullPunisher.aux: does; RootEntailment.poorlyAlignedRoot: "support" aligned badly to "criticized"; Structure.parentsMismatch: args have different parents, different relations: text "decision" <-prep_over-- "President_Bush" vs. hyp "decision" <-dobj-- "support", which aligned to text "criticized" args have different parents, different relations: text "go_to_go_to_war" <-infmod-- "decision" vs. hyp "go_to_war" <-prep_to-- "support", which aligned to text "criticized"
Hand-tuned score: -5.5500
Threshold: -11.4590


Inference ID: Cycorp-021

Txt: LEDs can last ten years, whereas an incandescent bulb typically lasts 5000 hours

Hyp: Incandescent bulbs do last longer than LEDs . (No.)

Incandescent
JJ
bulbs
NNS
do
VBP
last
RB
longer
RB
LEDs
NNP
.
.
LEDs:NNS 11.96   6.40 15.00 11.40 13.95   0.00 20.00
can:MD 19.96 16.69 15.67 17.12 18.95 17.12 10.00
last:VB 11.96 11.40   7.63   0.00 18.95 11.40 20.00
ten:NN 11.96   9.68 13.69 11.46 12.31 10.00 19.42
years:NNS 11.96   8.69 13.69 12.84 14.54 10.00 19.49
,:, 20.00 20.00 19.52 20.00 19.51 20.00   5.73
whereas:IN 20.00 20.00 20.00 20.00 20.00 20.00 20.00
an:DT 20.00 20.00 20.00 20.00 20.00 20.00 10.00
incandescent:NN   2.00   6.14 14.96 14.96 14.35   9.96 19.79
bulb:NN 11.96   0.50 13.66 11.40 13.95   6.40 20.00
typically:RB 11.96 14.28 19.58   9.96   5.29 14.96 19.79
lasts:VBZ 11.96 11.40   7.69 10.31 14.40 11.40 19.71
5000:JJ   9.96 11.40 11.46 11.96 11.96 11.96 20.00
hours:NNS 11.96   7.89 13.69 12.84 12.46 10.00 19.95
NO_WORD   9.00 10.00 10.00   9.00   9.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -29.2083
Features matched: RootEntailment.poorlyAlignedRoot: "do" aligned badly to "lasts"; Structure.relMismatch: text "LEDs" is nsubj of "last" while hyp "LEDs" is prep_than of "do" which aligned to text "lasts"
Hand-tuned score: -2.0000
Threshold: -11.4590


Inference ID: Cycorp-022

Txt: The "Just Picture It" workshop, sponsored by Oceanside Photo and Video, Inc. and taught by portrait photographer Gale Carlson, has received rave reviews.

Hyp: Is `` Just Picture It '' a photography workshop ? (Yes.)

Is
VBZ
``
``
Just
RB
Picture
VBG
It
PRP
''
''
a
DT
photography
NN
workshop
NN
?
.
The:DT 20.00 10.00 20.00 20.00 20.00 10.00 10.00 20.00 20.00 10.00
``:`` 20.00   0.00 20.00 20.00 20.00   1.06 10.00 20.00 20.00 10.00
Just:RB 19.96 20.00   0.00 19.96 15.00 20.00 20.00 14.96 14.96 20.00
Picture:VBG   9.34 20.00 19.96   0.00 15.00 20.00 20.00 15.00 14.34 20.00
It:PRP 15.00 20.00 20.00 15.00   0.00 20.00 20.00 12.00 12.00 20.00
'':'' 20.00   1.06 20.00 20.00 20.00   0.00 10.00 20.00 19.89   9.33
workshop:NN 14.34 20.00 14.96 14.34 12.00 19.89 20.00   7.71   0.00 20.00
,:, 20.00   6.83 20.00 20.00 20.00   6.68 10.00 19.37 19.76 10.00
sponsored:VBN   9.34 20.00 19.96   8.95 15.00 19.76 20.00 14.25 10.75 19.75
Oceanside_Photo_and_Video_,_Inc._and:NNP 15.17 20.50 15.46 11.19 12.50 20.50 20.50 10.46 10.17 20.50
taught:VBN   7.74 19.47 19.96   8.95 15.00 20.00 20.00 14.25 10.96 20.00
portrait:NN 14.34 20.00 14.96   7.08 12.00 20.00 20.00   7.62   7.79 20.00
photographer:NN 14.34 18.38 14.96 13.95 12.00 18.09 20.00   5.00   7.78 20.00
Gale_Carlson:NNP 15.46 20.50 15.46 15.46 12.50 20.50 20.50   8.97 10.46 20.50
,:, 20.50   7.33 20.50 20.50 20.50   7.18 10.50 19.87 20.26 10.50
has:VBZ   9.34 20.00 19.96   8.69 15.00 20.00 20.00 15.00 12.52 20.00
received:VBN 10.00 20.00 19.96 10.00 15.00 20.00 20.00 15.00 14.47 20.00
rave:JJ   9.74 18.71 11.96   8.36 15.00 19.62 20.00 10.71   7.13 19.37
reviews:NNS 14.34 18.81 14.96 10.45 12.00 18.20 20.00   6.36   7.29 20.00
.:. 20.00   7.32 20.00 20.00 20.00   6.80 10.00 20.00 20.00 10.00
NO_WORD   1.00 10.00   9.00 10.00 10.00 10.00   1.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -25.0000
Features matched: Adjunct.dropPosCxt: text adjunct "sponsored" of "workshop" dropped on aligned hyp word "workshop"; NullPunisher.article: a; NullPunisher.other: ?; NullPunisher.other: Is; Quant.contract: [the,a]; Structure.argsMismatch: args have different parents but same relations: text "``" <-punct-- "workshop vs. hyp "``" <-punct-- "Picture", which aligned to text "Picture" args have different parents but same relations: text "''" <-punct-- "workshop vs. hyp "''" <-punct-- "Picture", which aligned to text "Picture" args have different parents but same relations: text "workshop" <-nsubjpass-- "sponsored vs. hyp "workshop" <-dobj-- "Picture", which aligned to text "Picture" args have different parents, different relations: text "workshop" <-nsubj-- "received" vs. hyp "workshop" <-dobj-- "Picture", which aligned to text "Picture"
Hand-tuned score: -2.6000
Threshold: -11.4590


Inference ID: Cycorp-023

Txt: The equatorial diameter of Saturn is 10% larger than its polar diameter.

Hyp: Saturn is an ellipsoid . (Yes.)

Saturn
NNP
is
VBZ
an
DT
ellipsoid
NN
.
.
The:DT 20.50 20.00 10.00 20.00 10.00
equatorial:JJ 12.46 11.96 20.00 11.96 20.00
diameter:NN 10.50 15.00 20.00   5.41 19.61
Saturn:NNP   0.00 14.84 20.50 10.50 20.50
is:VBZ 14.84   0.00 20.00 15.00 20.00
10:CD 25.00 20.50 20.50 19.19 19.16
%:NN 15.00 15.50 20.50 10.50 20.50
larger:JJR 12.46 11.96 20.00 11.96 17.97
its:PRP$ 12.50 13.00 20.00 12.00 20.00
polar:JJ 12.46 11.96 20.00 11.96 20.00
diameter:NN 10.50 15.00 20.00   5.41 19.61
.:. 20.50 20.00 10.00 20.00   0.00
NO_WORD 10.00   1.00   1.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -11.4140
Features matched: Adjunct.dropPosCxt: text adjunct "polar" of "diameter" dropped on aligned hyp word "ellipsoid"; NullPunisher.aux: is; NullPunisher.article: an; RootEntailment.poorlyAlignedRoot: "ellipsoid" aligned badly to "diameter"; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "larger vs. hyp "." <-punct-- "ellipsoid", which aligned to text "diameter" text "Saturn" is prep_of of "diameter" while hyp "Saturn" is nsubj of "ellipsoid" which aligned to text "diameter"
Hand-tuned score: -3.6500
Threshold: -11.4590


Inference ID: Cycorp-024

Txt: The equatorial diameter of Saturn is 10% larger than its polar diameter.

Hyp: Saturn is a sphere . (No.)

Saturn
NNP
is
VBZ
a
DT
sphere
NN
.
.
The:DT 20.50 20.00 10.00 20.00 10.00
equatorial:JJ 12.46 11.96 20.00 11.22 20.00
diameter:NN 10.50 15.00 20.00   5.41 19.61
Saturn:NNP   0.00 14.84 20.50   7.97 20.50
is:VBZ 14.84   0.00 20.00 14.34 20.00
10:CD 25.00 20.50 20.50 19.19 19.16
%:NN 15.00 15.50 20.50 10.08 20.50
larger:JJR 12.46 11.96 20.00 11.96 17.97
its:PRP$ 12.50 13.00 20.00 12.00 20.00
polar:JJ 12.46 11.96 20.00   9.25 20.00
diameter:NN 10.50 15.00 20.00   5.41 19.61
.:. 20.50 20.00 10.00 20.00   0.00
NO_WORD 10.00   1.00   1.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -11.4140
Features matched: Adjunct.dropPosCxt: text adjunct "equatorial" of "diameter" dropped on aligned hyp word "sphere"; NullPunisher.article: a; NullPunisher.aux: is; Quant.contract: [the,a]; RootEntailment.poorlyAlignedRoot: "sphere" aligned badly to "diameter"; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "larger vs. hyp "." <-punct-- "sphere", which aligned to text "diameter" text "Saturn" is prep_of of "diameter" while hyp "Saturn" is nsubj of "sphere" which aligned to text "diameter"
Hand-tuned score: -2.6500
Threshold: -11.4590


Inference ID: Cycorp-025

Txt: Charlotte Jones gave birth to a healthy baby boy, Johnathan Daniel, on March 14th, 2004.

Hyp: Charlotte Jones was pregnant on December 14 , 2003 . (Yes.)

Charlotte_Jones
NNS
was
VBD
pregnant
JJ
December
NNP
14
CD
,
,
2003
CD
.
.
Charlotte_Jones:NNS   5.00 13.67 12.46 14.96 24.96 25.00 24.96 20.50
gave_birth:VBD 15.46 10.00 11.96 14.42 19.42 20.50 20.46 20.00
a:DT 20.50 20.00 20.00 20.50 20.50 10.50 20.50 10.00
healthy:JJ 12.46 11.96   6.37 12.46 20.37 20.50 20.46 19.46
baby:NN   9.52 14.34   5.63 10.50 20.50 19.20 20.46 19.63
boy:NN   9.52 14.34   6.78 10.50 20.50 19.17 20.46 19.66
,:, 25.00 20.50 19.69 20.00 18.78   0.00 19.45   6.23
Johnathan_Daniel:NNP 12.99 15.17 12.46 14.34 24.34 25.00 24.96 20.50
,:, 25.00 20.50 19.69 20.00 18.78   0.00 19.45   6.23
March:NNP 13.19 11.88 12.46   4.57 17.84 20.00 19.96 20.50
14th:CD 24.96 20.46 20.46 19.96   5.00 20.00   5.00 20.45
,:, 25.00 20.50 19.69 20.00 18.78   0.00 19.45   6.23
2004:CD 24.96 20.46 20.15 19.96   4.96 19.10   0.00 20.50
.:. 20.50 20.00 19.79 20.50 19.34   6.23 20.50   0.00
NO_WORD 10.00   1.00   9.00 10.00 10.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -27.1610
Features matched: Adjunct.dropPosCxt: text adjunct "14th" of "March" dropped on aligned hyp word "December"; Date.dateHeadMismatch: December vs. March; NullPunisher.aux: was; RootEntailment.poorlyAlignedRoot: "pregnant" aligned badly to "baby"; Structure.argsMismatch: args have different parents but same relations: text "Charlotte_Jones" <-nsubj-- "gave_birth vs. hyp "Charlotte_Jones" <-nsubj-- "pregnant", which aligned to text "baby" args have different parents but same relations: text "March" <-prep_on-- "gave_birth vs. hyp "December" <-prep_on-- "pregnant", which aligned to text "baby" args have different parents but same relations: text "." <-punct-- "gave_birth vs. hyp "." <-punct-- "pregnant", which aligned to text "baby"
Hand-tuned score: -6.5500
Threshold: -11.4590


Inference ID: Cycorp-026

Txt: Keikaimalu, a wholphin (whale-dolphin hybrid), has given birth to female calf.

Hyp: Keikaimalu did gave_birth to a ruminant . (No.)

Keikaimalu
NNP
did
VBD
gave_birth
NN
a
DT
ruminant
NN
.
.
Keikaimalu:NNP   0.00 15.46 10.46 20.50 10.46 20.50
,:, 20.50 19.80 20.00 10.00 20.00   5.73
a:DT 20.50 20.00 20.00   0.00 20.00 10.00
wholphin:NN 10.46 14.96   9.96 20.00   9.96 20.00
-LRB-:-LRB- 20.50 20.00 20.00 10.00 20.00 10.00
whale-dolphin:JJ 12.46 11.51 11.96 20.00 11.96 20.00
hybrid:NN 10.46 11.24   9.02 20.00   8.11 19.87
-RRB-:-RRB- 20.50 20.00 20.00 10.00 20.00 10.00
,:, 20.50 19.80 20.00 10.00 20.00   5.73
has:VBZ 15.46   7.53 13.76 20.00 14.34 20.00
given_birth:VBN 15.46   7.32   5.00 20.00 15.00 20.00
female:JJ 12.46 12.00 12.00 20.00   7.76 20.00
calf:NN 10.46 13.64 10.00 20.00   5.76 20.00
.:. 20.50 17.99 20.00 10.00 20.00   0.00
NO_WORD 10.00 10.00 10.00   1.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -21.0762
Features matched: Adjunct.dropPosCxt: text adjunct "female" of "calf" dropped on aligned hyp word "ruminant"; NullPunisher.article: a; RootEntailment.poorlyAlignedRoot: "did" aligned badly to "given_birth"
Hand-tuned score: -0.6000
Threshold: -11.4590


Inference ID: Cycorp-027

Txt: A wholphin is a whale-dolphin hybrid.

Hyp: The term does `` wholphin '' refer to a type of hybrid . (Yes.)

The
DT
term
NN
does
VBZ
``
``
wholphin
NN
''
''
refer
VBP
a
DT
type
NN
hybrid
NN
.
.
A:DT 10.00 20.00 20.00 10.00 20.00 10.00 20.00   0.00 20.00 20.00 10.00
wholphin:NN 20.00   9.96 14.96 20.00   0.00 20.00 14.96 20.00   9.96   9.96 20.00
is:VBZ 20.00 14.34   9.34 20.00 14.96 20.00   5.51 20.00 12.74 14.34 20.00
a:DT 10.00 20.00 20.00 10.00 20.00 10.00 20.00   0.00 20.00 20.00 10.00
whale-dolphin:JJ 20.00 11.96 11.21 20.00   7.00 19.85 11.13 20.00 11.34   9.67 20.00
hybrid:NN 20.00   5.91 13.05 20.00   9.96 20.00 14.48 20.00   6.67   0.00 19.87
.:. 10.00 19.66 20.00   7.32 20.00   6.80 19.97 10.00 17.87 19.87   0.00
NO_WORD   1.00 10.00 10.00 10.00 10.00 10.00 10.00   1.00 10.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -58.5544
Features matched: Adjunct.dropPosCxt: text adjunct "whale-dolphin" of "hybrid" dropped on aligned hyp word "hybrid"; NullPunisher.article: The; Quant.contract: [a,the]; Quant.contract: [a,a]; RootEntailment.poorlyAlignedRoot: "does" aligned badly to "is"; Structure.argsMismatch: args have different parents but same relations: text "." <-punct-- "hybrid vs. hyp "." <-punct-- "does", which aligned to text "is" args have different parents, different relations: text "is" <-cop-- "hybrid" vs. hyp "refer" <-ccomp-- "does", which aligned to text "is"
Hand-tuned score: -1.6000
Threshold: -11.4590


Inference ID: Cycorp-028

Txt: Marilyn Connors had a very difficult pregnancy and died in childbirth yesterday.

Hyp: Marilyn Connors is pregnant . (No.)

Marilyn_Connors
NNS
is
VBZ
pregnant
JJ
.
.
Marilyn_Connors:NNS   0.00 15.17 12.46 20.50
had:VBD 14.52   7.80 11.96 20.00
a:DT 20.50 20.00 20.00 10.00
very:RB 15.46 19.96 11.96 20.00
difficult:JJ 12.46 11.96   9.96 17.00
pregnancy:NN 10.46 15.00   3.75 19.77
died:VBD 14.97   8.07   7.91 20.00
childbirth:NN 10.46 15.00   5.16 20.00
yesterday:NN 10.46 15.00 11.96 18.11
.:. 20.50 20.00 19.79   0.00
NO_WORD 10.00   1.00   9.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -8.7539
Features matched: Adjunct.dropPosCxt: text adjunct "difficult" of "pregnancy" dropped on aligned hyp word "pregnant"; NullPunisher.aux: is; Structure.argsMismatch: args have different parents but same relations: text "Marilyn_Connors" <-nsubj-- "had vs. hyp "Marilyn_Connors" <-nsubj-- "pregnant", which aligned to text "pregnancy" args have different parents but same relations: text "." <-punct-- "had vs. hyp "." <-punct-- "pregnant", which aligned to text "pregnancy"
Hand-tuned score: -1.5500
Threshold: -11.4590


Inference ID: Cycorp-029

Txt: Serena Williams is a great tennis player, perhaps one of the best ever.

Hyp: Serena Williams does play tennis well . (Yes.)

Serena_Williams
NNS
does
VBZ
play
NN
tennis
NN
well
RB
.
.
Serena_Williams:NNS   5.00 14.55 10.46 10.46 14.97 20.50
is:VBZ 15.17   9.34 13.07 15.00 19.34 20.00
a:DT 20.50 20.00 20.00 20.00 20.00 10.00
great:JJ 12.46 11.01   8.17 10.79 11.96 17.92
tennis_player:NN   7.17 13.11   5.00   0.00 13.95 20.00
,:, 20.50 19.26 19.21 20.00 20.00   5.73
perhaps:RB 15.46 19.96 14.96 14.96   9.96 20.00
one:CD 24.96 20.50 17.49 20.50 19.19 20.50
the:DT 20.50 18.65 20.00 20.00 20.00 10.00
best:JJS 11.52   9.70   7.41   8.49 10.95 18.78
ever:RB 15.46 17.36 14.96 14.96   9.96 20.00
.:. 20.50 20.00 18.13 20.00 20.00   0.00
NO_WORD 10.00 10.00 10.00 10.00   9.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -36.1080
Features matched: Adjunct.addPosCxt: hyp added well[well-RB]; Adjunct.dropPosCxt: text adjunct "ever" of "tennis_player" dropped on aligned hyp word "tennis"; Modal.dontKnow: possible -> actual; NullPunisher.other: well; RootEntailment.poorlyAlignedRoot: "does" aligned badly to "tennis_player"
Hand-tuned score: -4.5000
Threshold: -11.4590


Inference ID: Cycorp-30

Txt: War and Peace is a very long novel.

Hyp: War and Peace does contain more pages than the average novel . (Yes.)

War
NNP
Peace
NNP
does
VBZ
contain
VB
more
JJR
pages
NNS
the
DT
average
JJ
novel
NN
.
.
War:NNP   0.00   7.94 15.00 15.00 12.00 10.00 20.00 12.00 10.00 20.00
Peace:NNP   7.94   0.00 15.50 15.50 12.50 10.50 20.50 10.40   7.27 20.50
is:VBZ 15.00 15.50   9.34   8.33 11.34 12.34 20.00 10.33 14.34 20.00
a:DT 20.00 20.50 20.00 20.00 20.00 20.00 10.00 20.00 20.00 10.00
very:RB 14.96 15.46 19.96 19.96 11.96 14.96 20.00 11.96 14.96 20.00
long:JJ 12.00 11.19 11.33 12.00   8.25 12.00 20.00 10.00 10.69 17.94
novel:NN 10.00   7.27 13.95 13.75 10.95   6.58 20.00 12.00   0.00 19.66
.:. 20.00 20.50 20.00 18.50 20.00 20.00 10.00 19.31 19.66   0.00
NO_WORD 10.00 10.00   1.00 10.00   9.00 10.00   1.00   9.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -42.1560
Features matched: Adjunct.addPosCxt: hyp added average[average-JJ]; Adjunct.dropPosCxt: text adjunct "very" of "long" dropped on aligned hyp word "more"; NullPunisher.aux: does; NullPunisher.article: the; NullPunisher.other: average; Quant.contract: [a,the]; RootEntailment.poorlyAlignedRoot: "contain" aligned badly to "is"; Structure.argsMismatch: args have different parents but same relations: text "War" <-nsubj-- "novel vs. hyp "War" <-nsubj-- "contain", which aligned to text "is" args have different parents but same relations: text "." <-punct-- "novel vs. hyp "." <-punct-- "contain", which aligned to text "is"
Hand-tuned score: -4.6500
Threshold: -11.4590


Inference ID: Cycorp-031

Txt: Ambassador Richard C. Holbrooke will visit Paris, France from Saturday, April 22 until Tuesday, April 25.

Hyp: Ambassador Holbrooke will be in Paris on April 24th . (Yes.)

Ambassador
NNP
Holbrooke
NNP
will
MD
be
VB
Paris
NNP
April
NNP
24th
JJ
.
.
Ambassador:NNP   0.00   9.29 20.00 14.34   9.84 10.50 12.46 20.00
Richard_C._Holbrooke:NNP 10.46   0.00 20.46 15.46 14.96 14.96 16.96 20.50
will:MD 20.00 20.46   0.00 20.00 20.50 19.19 20.46 10.00
visit:VB 15.00 15.46 20.00   7.74 13.63 15.50 11.05 20.00
Paris:NNP   9.84 14.96 20.50 14.84   0.00 15.00 16.96 20.50
,:, 20.50 25.00 10.50 20.50 25.00 20.00 20.00   6.23
France:NNP   8.55 14.96 20.50 14.84   2.00 15.00 16.96 20.50
Saturday:NNP 10.50 14.96 19.19 15.50 15.00   7.23 11.96 20.50
,:, 20.50 25.00 10.50 20.50 25.00 20.00 20.00   6.23
April:NNP 10.50 14.96 19.19 15.50 15.00   0.00 11.96 20.50
22:CD 20.50 24.96 19.19 20.50 25.00 17.84 19.56 19.32
Tuesday:NNP 10.50 14.96 19.19 15.50 15.00   7.23 11.96 20.50
,:, 20.50 25.00 10.50 20.50 25.00 20.00 20.00   6.23
April:NNP 10.50 14.96 19.19 15.50 15.00   0.00 11.96 20.50
25:CD 20.50 24.96 19.19 20.50 25.00 17.84 19.96 19.52
.:. 20.00 20.50 10.00 20.00 20.50 20.50 20.50   0.00
NO_WORD 10.00 10.00 10.00 10.00 10.00 10.00   9.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -20.7439
Features matched: Adjunct.dropPosCxt: text adjunct "22" of "April" dropped on aligned hyp word "April"; Date.matchDatesByGraph: hyp/txt matching, by graph: April and children; Date.hypDateIns: hypothesis date insertion: 24th; NullPunisher.other: 24th; RootEntailment.poorlyAlignedRoot: "be" aligned badly to "visit"; Structure.relMismatch: text "Paris" is dobj of "visit" while hyp "Paris" is prep_in of "be" which aligned to text "visit"
Hand-tuned score: -3.5000
Threshold: -11.4590


Inference ID: Cycorp-032

Txt: The Island Nut Sampler includes an 8 ounce box of milk chocolate covered macadamia nuts and an 8 ounce box of white chocolate covered macadamia nuts.

Hyp: It does include some dark-chocolate covered macadamia nuts . (No.)

It
PRP
does
VBZ
include
VB
some
DT
dark-chocolate
JJ
covered
JJ
macadamia
NN
nuts
NNS
.
.
The:DT 20.00 20.00 20.00 10.00 20.00 20.00 20.00 20.00 10.00
Island:NNP 12.50 14.45 15.50 20.50 12.46 11.45   9.45   9.45 20.50
Nut:NNP 12.50 13.61 15.50 20.50 12.46   8.96   8.61   0.81 20.50
Sampler:NNP 12.50 13.61 15.50 20.50 12.46 10.53   8.61   8.53 20.50
includes:VBZ 15.00   9.55   0.50 20.00 11.96   7.64 14.87 15.00 19.56
an:DT 20.00 17.89 20.00 10.00 20.00 20.00 20.00 20.00 10.00
8:CD 20.50 20.50 20.50 20.50 19.13 19.42 20.50 18.34 19.96
ounce:NN 12.00 10.17 15.00 20.00 11.66 10.95   8.11   7.84 19.86
box:NN 12.00 13.08 12.42 20.00   8.60   6.85   4.40   7.81 19.82
milk_chocolate:NN 12.00 14.34 12.87 20.00   7.00 10.81   8.53   8.44 20.00
covered:VBN 15.00   8.49   5.64 20.00   8.32   0.00 13.95 11.46 19.33
macadamia:NN 12.00 13.11 13.91 20.00   7.79 10.95   0.00   5.49 19.94
nuts:NNS 12.00 13.11 15.00 20.00   6.73   8.46   5.49   0.00 19.80
an:DT 20.00 17.89 20.00 10.00 20.00 20.00 20.00 20.00 10.00
8:CD 20.50 20.50 20.50 20.50 19.13 19.42 20.50 18.34 19.96
ounce:NN 12.00 10.17 15.00 20.00 11.66 10.95   8.11   7.84 19.86
box:NN 12.00 13.08 12.42 20.00   8.60   6.85   4.40   7.81 19.82
white_chocolate:NN 12.00 14.05 13.81 20.00   7.00   9.89   9.05   8.44 20.00
covered:VBD 15.00   8.49   5.64 20.00   8.32   0.00 13.95 11.46 19.33
macadamia:NN 12.00 13.11 13.91 20.00   7.79 10.95   0.00   5.49 19.94
nuts:NNS 12.00 13.11 15.00 20.00   6.73   8.46   5.49   0.00 19.80
.:. 20.00 20.00 19.86 10.00 19.36 19.33 19.94 19.80   0.00
NO_WORD 10.00   1.00 10.00 10.00   9.00   9.00 10.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -34.2319
Features matched: NullPunisher.other: It; NullPunisher.other: some; NullPunisher.aux: does; Structure.argsMismatch: args have different parents but same relations: text "nuts" <-dobj-- "covered vs. hyp "nuts" <-dobj-- "include", which aligned to text "includes"
Hand-tuned score: -4.0500
Threshold: -11.4590


Inference ID: Cycorp-033

Txt: A quarter of all cellphones have built-in cameras.

Hyp: Do most cell_phones have a lens . (No.)

Do
VB
most
JJS
cell_phones
NNS
have
VB
a
DT
lens
NN
.
.
A:DT 20.00 20.00 20.00 20.00   0.00 20.00 10.00
quarter:NN 10.67 11.96   9.02 12.61 20.00   7.90 19.74
all:DT 20.00 20.00 20.00 20.00 10.00 20.00 10.00
cellphones:NNS 15.00 11.96   1.90 13.95 20.00   3.53 20.00
have:VBP   7.32 11.96 12.80   0.00 20.00 13.95 20.00
built-in:JJ 11.96   9.96 11.96 11.96 20.00 11.96 20.00
cameras:NNS 15.00 11.96   6.77 13.95 20.00   3.53 19.47
.:. 20.00 20.00 20.00 20.00 10.00 20.00   0.00
NO_WORD 10.00   9.00 10.00 10.00   1.00 10.00 10.00

Response: yes (INCORRECT)
Justification:
Alignment score: -26.7570
Features matched: Adjunct.addPosCxt: hyp added most[most-JJS]; Adjunct.dropPosCxt: text adjunct "built-in" of "cameras" dropped on aligned hyp word "lens"; Polarity.hypNegMarker: "most": JJS; NullPunisher.article: a; NullPunisher.other: most; Quant.contract: [all,most]; RootEntailment.poorlyAlignedRoot: "Do" aligned badly to "have"
Hand-tuned score: -1.6000
Threshold: -11.4590


Inference ID: Cycorp-034

Txt: Three quarters of all cellphones have a built-in camera.

Hyp: Do most cell_phones have a lens . (Yes.)

Do
VB
most
JJS
cell_phones
NNS
have
VB
a
DT
lens
NN
.
.
Three:CD 19.19 20.46 19.84 20.50 20.50 20.50 20.50
quarters:NNS 15.00 11.96   8.53 13.95 20.00   8.03 19.46
all:DT 20.00 20.00 20.00 20.00 10.00 20.00 10.00
cellphones:NNS 15.00 11.96   1.90 13.95 20.00   3.53 20.00
have:VBP   7.32 11.96 12.80   0.00 20.00 13.95 20.00
a:DT 20.00 20.00 20.00 20.00   0.00 20.00 10.00
built-in:JJ 11.96   9.96 11.96 11.96 20.00 11.96 20.00
camera:NN 15.00 11.96   6.77 13.95 20.00   3.53 18.65
.:. 20.00 20.00 20.00 20.00 10.00 20.00   0.00
NO_WORD 10.00   9.00 10.00 10.00   1.00 10.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -25.7570
Features matched: Adjunct.addPosCxt: hyp added most[most-JJS]; Adjunct.dropPosCxt: text adjunct "built-in" of "camera" dropped on aligned hyp word "lens"; Polarity.hypNegMarker: "most": JJS; NullPunisher.other: most; Quant.contract: [all,most]; Quant.contract: [a,a]; RootEntailment.poorlyAlignedRoot: "Do" aligned badly to "have"
Hand-tuned score: -0.5000
Threshold: -11.4590


Inference ID: Cycorp-035

Txt: Marilyn Connors had a very difficult pregnancy and died in childbirth yesterday.

Hyp: Marilyn Connors was pregnant . (Yes.)

Marilyn_Connors
NNS
was
VBD
pregnant
JJ
.
.
Marilyn_Connors:NNS   0.00 15.17 12.46 20.50
had:VBD 14.52   9.34 11.96 20.00
a:DT 20.50 20.00 20.00 10.00
very:RB 15.46 19.96 11.96 20.00
difficult:JJ 12.46 11.96   9.96 17.00
pregnancy:NN 10.46 15.00   3.75 19.77
died:VBD 14.97   9.34   7.91 20.00
childbirth:NN 10.46 15.00   5.16 20.00
yesterday:NN 10.46 15.00 11.96 18.11
.:. 20.50 20.00 19.79   0.00
NO_WORD 10.00   1.00   9.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -8.7539
Features matched: Adjunct.dropPosCxt: text adjunct "difficult" of "pregnancy" dropped on aligned hyp word "pregnant"; NullPunisher.aux: was; Structure.argsMismatch: args have different parents but same relations: text "Marilyn_Connors" <-nsubj-- "had vs. hyp "Marilyn_Connors" <-nsubj-- "pregnant", which aligned to text "pregnancy" args have different parents but same relations: text "." <-punct-- "had vs. hyp "." <-punct-- "pregnant", which aligned to text "pregnancy"
Hand-tuned score: -1.5500
Threshold: -11.4590


Inference ID: Cycorp-036

Txt: Marilyn Connors had a very difficult pregnancy and died in childbirth yesterday.

Hyp: Marilyn Connors is dead . (Yes.)

Marilyn_Connors
NNS
is
VBZ
dead
JJ
.
.
Marilyn_Connors:NNS   0.00 15.17 12.46 20.50
had:VBD 14.52   7.80 12.00 20.00
a:DT 20.50 20.00 20.00 10.00
very:RB 15.46 19.96 11.96 20.00
difficult:JJ 12.46 11.96   9.96 17.00
pregnancy:NN 10.46 15.00   9.39 19.77
died:VBD 14.97   8.07   5.77 20.00
childbirth:NN 10.46 15.00   8.86 20.00
yesterday:NN 10.46 15.00   9.84 18.11
.:. 20.50 20.00 18.65   0.00
NO_WORD 10.00   1.00   9.00 10.00

Response: yes (CORRECT)
Justification:
Alignment score: -10.7745
Features matched: Adjunct.dropPosCxt: text adjunct "yesterday" of "died" dropped on aligned hyp word "dead"; NullPunisher.aux: is; RootEntailment.poorlyAlignedRoot: "dead" aligned badly to "died"; Structure.argsMismatch: args have different parents but same relations: text "Marilyn_Connors" <-nsubj-- "had vs. hyp "Marilyn_Connors" <-nsubj-- "dead", which aligned to text "died" args have different parents but same relations: text "." <-punct-- "had vs. hyp "." <-punct-- "dead", which aligned to text "died"
Hand-tuned score: -3.5500
Threshold: -11.4590


Word similarity table built on Wed Jul 05 15:16:09 PDT 2006 using command:
java edu.stanford.nlp.rte.WordSimilarityGenerator -info /u/nlp/rte/data/byformat/align/stochastic/cycorp_dev.pipeline.align.xml -output /u/nlp/rte/data/byformat/wordsim/stochastic/cycorp_dev.pipeline.wordsim.html -lex.BasicWN off