Yejin Choi

Ph.D. Student  Cornell University  Computer Science Department  4162 Upson Hall  Ithaca, NY 14853

Research Interest:

NLP, machine learning, AI.

My advisor is Claire Cardie.
I am also taking a minor in Operations Research, focusing on statistics. 

Publications:

• Adapting a Polarity Lexicon Using Integer Linear Programming for Domain-Specific Sentiment Classification.
  Yejin Choi and Claire Cardie.
  Empirical Methods in Natural Language Processing (EMNLP), 2009.
• Learning with Compositional Semantics as Structural Inference for Subsentential Sentiment Analysis.
  Yejin Choi and Claire Cardie.
  Empirical Methods in Natural Language Processing (EMNLP), 2008.
• Structured Local Training and Biased Potential Functions for Conditional Random Fields with Application to Coreference Resolution
  Yejin Choi, Claire Cardie.
  Human Language Technologies: the Conference of the North American Chapter of the Association for Computational Linguistics (NAACL-HLT), 2007.
• Identifying Expressions of Opinion in Context.
  Eric Breck, Yejin Choi, Claire Cardie.
  International Joint Conference on Artificial Intelligence (IJCAI), 2007.
• Cornell System Description for the NTCIR-6 Opinion Task.
  Eric Breck, Yejin Choi, Veselin Stoyanov, and Claire Cardie.
  The 6th NTCIR Workshop Meeting , 2007.
• Joint Extraction of Entities and Relations for Opinion Recognition.
  Yejin Choi, Eric Breck, Claire Cardie.
  Empirical Methods in Natural Language Processing (EMNLP), 2006.
• Identifying Sources of Opinions with Conditional Random Fields and Extraction Patterns.
  Yejin Choi, Claire Cardie, Ellen Riloff, and Siddharth Patwardhan.
  Human Language Technology Conference/Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP), 2005.
• OpinionFinder: A system for subjectivity analysis.
  Theresa Wilson, Paul Hoffmann, Swapna Somasundaran, Jason Kessler, Janyce Wiebe, Yejin Choi, Claire Cardie, Ellen Riloff and Siddharth Patwardhan.
  A demo at Human Language Technology Conference/Conference on Empirical Methods in Natural Language Processing (HLT-EMNLP), 2005.
  

Patents:

• Sparse caching for streaming media.
  A. Grigorovitch, Y. Choi , T. Carvalho.
  [Patent 20050066063] filed by Microsoft Corporation, 2003.
• Midstream determination of varying bandwidth availability.
  T. Batterberry, A. Grigorovitch, A. Klemets, J. Stewart, Y. Choi
  [Patent 20040267503] filed by Microsoft Corporation, 2003.
• System and method for automatically recovering from failed network connections in streaming media scenarios.
  Y. Choi , A. Grigorovitch, T. Batterberry
  [Patent 20030236905] filed by Microsoft Corporation, 2002.

Brief history:

• Before coming here, I spent three years at Microsoft in US as a software design engineer. I worked with Windows Media Platform Group for Windows Media Server and Player suite. My work was focused on automatic connection/session recovery, client side caching, implementation of HTTP/RTSP/RTP protocol stacks and dynamic bandwidth controlling. I have co-authored three US patents during my stay.
  
  
• Prior to then, I worked at LG Electronics Research Center in Seoul, Korea, as a research staff for half a year, developing HDTV data broadcast software solutions. The project was to embed internet web data into MPEG2 stream, along with digital TV signal, and to forward the demultiplexed web stream via MPEG2 decoder through virtual NDIS driver so that users can access the web data as if it has been transmitted over IP. Our work was presented at 1999 Comdex at Las Vegas.
  
  
• I received my BS degree in Computer Science and Engineering at Seoul National University in Korea.
  

Coursework:

TA: