News

I graduated in August 2009 and joined Google in October 2009.

Contact info

Pi-Chuan Chang (張碧娟)
NLP Group, AI Lab
Computer Science Department, Stanford University

Advisor: Prof. Chris Manning
Email: pcchang -at- cs.stanford.edu

Stanford University's Arabic-to-English Statistical Machine Translation System for the 2009 NIST Evaluation,
Michel Galley, Spence Green, Daniel Cer, Pi-Chuan Chang, Christopher D. Manning.
The 2009 NIST Open Machine Translation Evaluation Meeting.
[pdf]

Improving Chinese-English Machine Translation through Better Source-side Linguistic Processing,
PhD thesis, July 2009.
[pdf | defense slides]
Discriminative Reordering with Chinese Grammatical Relations Features,
Pi-Chuan Chang, Huihsin Tseng, Dan Jurafsky, and Christopher D. Manning.
in NAACL 2009 Third Workshop on Syntax and Structure in Statistical Translation.
[pdf | slides]
update (June 04, 2009): two corrections: (1) added a new footnote 1 to explain in more detail how PATH features are extracted; (2) updated the numbers in the last column of Table 3. We accidentally included a different set of experiments. This was found when I was making the slides.
Disambiguating "DE" for Chinese-English Machine Translation,
Pi-Chuan Chang, Dan Jurafsky and Christopher D. Manning.
in EACL 2009 Fourth Workshop on Statistical Machine Translation.
[pdf | slides]
update (April 02, 2009): correct errors in footnote 9 about the LDC corpora I used.

Optimizing Chinese Word Segmentation for Machine Translation Performance,
Pi-Chuan Chang, Michel Galley and Christopher D. Manning.
in ACL 2008 Third Workshop on Statistical Machine Translation.
[pdf | slides]

Stanford University's Chinese-to-English Statistical Machine Translation System for the 2008 NIST Evaluation,
Michel Galley, Pi-Chuan Chang, Daniel Cer, Jenny R. Finkel, Christopher D. Manning.
in Proceedings of the 2008 NIST Open Machine Translation Evaluation Workshop.
[pdf]

A Discriminative Syntactic Word Order Model for Machine Translation,
Pi-Chuan Chang and Kristina Toutanova.
in ACL 2007.
[pdf | slides]

Automatically Detecting Action Items in Audio Meeting Recordings,
William Morgan, Pi-Chuan Chang, Surabhi Gupta and Jason M. Brenier.
in Proceedings of the 7th SIGdial Workshop on Discourse and Dialogue.
[pdf | poster]

A Conditional Random Field Word Segmenter for SIGHAN Bakeoff 2005,
Huihsin Tseng, Pichuan Chang, Galen Andrew, Daniel Jurafsky, Christopher D. Manning. 2005.
Fourth SIGHAN Workshop on Chinese Language Processing.
[pdf]

基於語料庫及辭典精緻化之中文語言模型強化之研究
(Chinese Language Modeling Enhancement by Corpora and Lexicon Refinement)
Masters thesis, June 2004.
[pdf]

Improved Language Model Adaptation Using Existing and Derived External Resources,
Pi-Chuan Chang and Lin-Shan Lee, ASRU 2003, St. Thomas, Virgin Islands, USA.
[pdf | poster]

Improved Chinese Broadcast News Transcription by Language Modeling with Temporally Consistent Training Corpora and Iterative Phrase Extraction,
Pi-Chuan Chang, Shuo-Peng Liao and Lin-Shan Lee, Eurospeech 2003, Geneva, Switzerland.
[ps | slides]