Weiwei Guo 郭维玮

I am a fourth year PhD student in the Department of Computer Science at Columbia University. I am affiliated with the Natural Language Processing Group and the Center for Computational Learning Systems. My advisor is Dr. Mona Diab. I received my B.S. in computer science from Sun Yat-sen University in 2007, and M.S. from Columbia University in 2009.

News

• 05/12/2013 Released the data and code in ACL2013 paper
• 04/24/2013 Gave a guest lecture at Indiana University, in my friend Muhammad Abdul-Mageed's class social media mining.
• 04/07/2013 One paper accepted at ACL 2013.
• 02/14/2013 One paper accepted at NAACL 2013.
• 01/21/2013 Started interning at Honda Research.
• 11/19/2012 Passed the candidacy exam!
• 10/19/2012 Talk at UMD, College Park.
• 10/13/2012 Released the code of Weighted Textual Matrix Factorization in my acl2012 paper.

Research

My research interest lies in natural language processing and machine learning. It can be summarized into the following topics:

• topic models and matrix factorization
• lexical semantics (word sense disambiguation)
• social media analysis

The projects I have worked on are:

• Enrich a tweet by linking it to a relevant news article in the weighted matrix factorization framework
• Weighted matrix factorization for more nuanced and robust short text/sentence semantics
• Subgroup detection in online discussion forums
• Incorporating lexical semantics in topic models
• Word sense disambiguation using multilingual evidence

Publications

• 2013

[13] Weiwei Guo, Hao Li, Heng Ji and Mona Diab. "Linking Tweets to News: A Framework to Enrich Online Short Text Data in Social Media". In Proceedings of ACL, 2013, Sofia, Bulgaria.

[12] Weiwei Guo and Mona Diab. "Improving Lexical Semantics for Sentential Semantics: Modeling Selectional Preference and Similar Words in a Latent Variable Model". In Proceedings of NAACL, 2013, Atlanta, Georgia, USA.

[11] Rebecca J. Passonneau, Emily Chen, Weiwei Guo and Dolores Perin. "Automated Pyramid Scoring of Summaries using Distributional Semantics". In Proceedings of ACL, 2013, Sofia, Bulgaria.

[10] Eneko Agirre, Daniel Cer, Mona Diab, Aitor Gonzalez-Agirre and Weiwei Guo. "*SEM 2013 shared task: Semantic Textual Similarity". In Proceedings of *SEM, 2013, Atlanta, Georgia, USA.

• 2012

[9] Weiwei Guo and Mona Diab. "Modeling Sentences in the Latent Space". In Proceedings of ACL, 2012, Jeju, Korea.[code]

[8] Weiwei Guo and Mona Diab. "Learning the Latent Semantics of a Concept by its Definition". In Proceedings of ACL, 2012, Jeju, Korea. [data]

[7] Pradeep Dasigi, Weiwei Guo and Mona Diab. "Genre Independent Subgroup Detection in Online Discussion Threads: A Pilot Study of Implicit Attitude using Latent Textual Semantics". In Proceedings of ACL, 2012, Jeju, Korea.

[6] Weiwei Guo and Mona Diab. "COL-WTMF: A Simple Unsupervised Latent Semantics based Approach for Sentence Similarity". In Proceedings of the 6th International Workshop on Semantic Evaluation, NAACL, 2012, Montreal, Canada.

• 2011

[5] Weiwei Guo and Mona Diab. "Semantic Topic Models: Combining Word Distributional Statistics and Dictionary Definitions". In Proceedings of EMNLP, 2011, Edinburgh, UK.

• 2010

[4] Weiwei Guo and Mona Diab. "Combining Orthogonal Monolingual and Multilingual Sources of Evidence for All Words WSD". In Proceedings of ACL, 2010, Uppsala, Sweden.

[3] Weiwei Guo and Mona Diab. "COLEUR and COLSLM: A WSD approach to Multilingual Lexical Substitution, Tasks 2 and 3 SemEval 2010". In Proceedings of 5th International Workshop on Semantic Evaluation, ACL, 2010, Uppsala, Sweden.

• 2009

[2] Weiwei Guo and Mona Diab. "Improvements to Monolingual English Word Sense Disambiguation". In Proceedings of the NAACL HLT Workshop on Semantic Evaluation: Recent Achievement and Future Directions, 2009, Boulder, Colorado, USA.

[1] Mona Diab, Lori Levin, Teruko Mitamura, Owen Rambow, Vinodkumar Prabhakaram and Weiwei Guo. "Committed Belief Annotation and Tagging". In Proceedings of the Third on Linguistic Annotation Workshop, ACL-IJCNLP, 2009, Morristown, NJ, USA.

Links

Semantic Textual Similarity (STS) Workshop

Personal

In my spare time I enjoy skiing, billiard and watching Arsenal games. I am the most authoritative expert on Arsenal FC in US:)