CS 775: Seminar in Natural Language Understanding
(The NLP Seminar)

Fall 2006
Mondays, 3:45-4:45 p.m., Upson 5126

This weekly graduate-level seminar involves presentation and/or discussion of recent research results in natural language processing, computational linguistics, and related fields as relevant (e.g., information retrieval or machine learning). To sign up to receive seminar announcements, please contact the Fall 2006 organizer, Lillian Lee.

Date	Event/paper/Emcee
Aug 28	Organizational meeting - we decided to move the meeting time to 3:45-4:45, still on Mondays.
Sep 11	John Blitzer, Ryan McDonald, and Fernando Pereira. Domain Adaptation with Structural Correspondence Learning. EMNLP 2006 . Introduced by Eric. [pdf]
Sep 18	Rion Snow, Daniel Jurafsky and Andrew Y. Ng. Semantic Taxonomy Induction from Heterogenous Evidence. ACL 2006. Introduced by Ves. [pdf]
Oct 2	Noah A. Smith and Jason Eisner. Annealing techniques for unsupervised statistical language learning. ACL 2004. Introduced by Yejin. [pdf]
Oct 9	no meeting (Fall Break). However, at 12:15 on Oct 13, Upson 5130, Prof. Xiaoyan Zhu is speaking about "ONBIRES: A Platform for Information Extraction from Biomedical Literature". [link to abstract]
Oct 30	X. Wei and W. Bruce Croft. "LDA-Based Document Models for Ad-hoc Retrieval". SIGIR 2006. Introduced by Asif. [pdf]
Nov 6	Helmut Schmid. Trace Prediction and Recovery With Unlexicalized PCFGs and Slash Features. COLING/ACL 2006 [pdf] Introduced by Effi.
Nov 13	Qiaozhu Mei and ChengXiang Zhai. Discovering Evolutionary Theme Patterns from Text -- An Exploration of Temporal Text Mining. KDD 2005, pp. 198--207. [pdf] Introduced by Benyah.
Nov 20	Hal Daumé, John Langford, and Daniel Marcu. SEARN in practice. Manuscript, 2006 [pdf]. Introduced by Rajat.
Nov 27	Andrew Goldberg and Xiaojin Jerry Zhu. Seeing stars when there aren't many stars: Graph-based semi-supervised learning for sentiment categorization. HLT-NAACL 2006 workshop - Textgraphs: Graph-based Algorithms for Natural Language Processing. Introduced by Janani. [pdf]

Possible sources for recent papers, in no particular order: COLING/ACL 2006 proceedings, SIGIR 2006 proceedings, HLT NAACL 2006 proceedings, EMNLP 2006, CoNLL 2006 (Cornell NLP-group alum wins best paper award!), EACL 2006. Some specific papers of possible interest that have not already been claimed (obviously not an exclusive list):

• Rie Kubota Ando. Applying Alternating Structure Optimization to Word Sense Disambiguation. CoNLL 2006 (best paper award) [pdf]
• David Kauchak and Regina Barzilay. Paraphrasing for automatic evaluation. HLT-NAACL 2006 [ps]
• David Blei and John Lafferty. Dynamic topic models. ICML 2006 [pdf]
• Ben Carterette, James Allan, and Ramesh Sitaraman. Minimal test collections for retrieval evaluation. SIGIR 2006 (best paper award) [pdf]
• Andrew Goldberg and Xiaojin Jerry Zhu. Seeing stars when there aren't many stars: Graph-based semi-supervised learning for sentiment categorization. TextGraphs: HLT NAACL 2006 Workshop on Graph-based Algorithms for Natural Language Processing [pdf]
• Guy Lebanon. Sequential Document Representations and Simplicial Curves. UAI 2006 [pdf]
• Wei Li and Andrew McCallum. Pachinko Allocation: DAG-structured Mixture Models of Topic Correlations. ICML 2006. [pdf]
• Christopher D. Manning. Local Textual Inference: It's hard to circumscribe, but you know it when you see it — and NLP needs it. Manuscript, 2006 [pdf]
• Gilad Mishne, David Carmel, and Ronny Lempel. Blocking blog spam with language model disagreement. Workshop on Adversarial Information Retrieval on the Web, 2005. [pdf]
• Claude St-Jacques and Caroline Barrière. Similarity judgments: Philosophical, psychological and mathematical investigations. Workshop on Linguistic Distances, 2006 [pdf]

Previous runnings: F98, S00, S01 (as Statistical Natural Language Processing: Models and Methods), F01, S02, F02, S03, F03, S04, F04,S05, F05, S06,

See also the Cornell NLP page and the Cornell machine learning page.

You may have come here from the the list of Cornell CS course websites