Lecture Notes and Assigned Readings

Date	Lecture Topic and Handouts	Readings	Assignments
Mon 1/24	Introduction (.pdf)	Jurafsky and Martin, Chapter 1.
Weds 1/26	Ambiguity in Language; a Bit o' History (.pdf)	L. Lee. "I'm sorry Dave, I'm afraid I can't do that'': Linguistics, Statistics, and Natural Language Processing circa 2001. To appear in the National Academies' Study on Fundamentals of Computer Science.
Mon 1/31	Lexical semantics (.pdf)	J&M: 16.1; 16.2; 16.4	Paper critique due. Burstein et al., Automated Scoring Using A Hybrid Feature Identification Technique, COLING-ACL, 1998.
Weds 2/2	NO CLASS
Mon 2/7	Word sense disambiguation (.pdf)	J&M: 17.1-17.2. For a description of the relevant background material on probability theory, see Manning and Schuetze 2.1.1-2.1.3.
Weds 2/9	Research paper presentation: Harlan Crystal	J&M: 17.1-17.2. For a description of the relevant background material on probability theory, see Manning and Schuetze 2.1.1-2.1.3.	Paper critiques (2) due. Yarowsky, D. Word-Sense Disambiguation Using Statistical Models of Roget's Categories Trained on Large Corpora. In Proceedings, COLING-92,1992. Yarowsky, D. Unsupervised Word Sense Disambiguation Rivaling Supervised Methods. In Proceedings of the 33rd Annual Meeting of the Association for Computational Linguistics, 1995.
Mon 2/14	Noisy channel model (.pdf)	J&M, Chapter 5.1-5.8
Weds 2/16	N-gram models (.pdf)	J&M, Chapter 6.1-6.6
Mon 2/21	finish N-gram models; Part-of-speech tagging (.pdf)	J&M, Chapter 8.1-8.4
Weds 2/23	Research paper presentation: Eli Rosofsky (Banko & Brill .pdf) (Kubota and Lee .pdf)		Paper critiques (2) due. Banko & Brill. "Scaling to Very Very Large Corpora for Natural Language Disambiguation," ACL 2001. Mostly-Unsupervised Statistical Segmentation of Japanese: Applications to Kanji. Rie Kubota Ando and Lillian Lee. First Conference of the NAACL, pp. 241--248, 2000.
Mon 2/28	HMM's for part-of-speech tagging (.pdf)	J&M, Chapter 8.5-8.8. The Viterbi algorithm is explained in Chapter 7. Alternatively, see this HMM tutorial.
Weds 3/2	Research paper presentation: Lisi Cai (.pdf) and Alec Rivers (.pdf)		Paper critiques (2) due. Cutting et al. A Practical Part-of-Speech Tagger. ANLP, 1992. Christer Samuelsson; Atro Voutilainen. Comparing a Linguistic and a Stochastic Tagger. ACL/EACL 1997.
Mon 3/7	Parsing (.pdf)	J&M, Chapters 9, 10, 12.	Project proposals due.
Weds 3/9	Research paper presentation: Paul Chen (.pdf) and Dustin Shultz (.pdf)	J&M 6.3	Paper critiques (2) due. (These were originally scheduled to follow the n-gram models lecture. You will need to have read J&M 6.3, on smoothing BEFORE tackling theses papers.) Michael Collins and James Brooks, 1995. Prepositional Attachment through a Backed-off Model. Third Workshop on Very Large Corpora, pp. 27--38. Stanley F. Chen and Joshua Goodman, 1996. An empirical study of smoothing techniques for language modeling Proceedings of the 34th Meeting of the Association for Computational Linguistics, pp 310--318.
Mon 3/14	Research paper presentation: Benyah Shaparenko (.pdf)		Paper critiques (2) due. (See 3/7 for associated readings from J&M.) Eugene Charniak, 1997. Statistical Parsing with a Context-free Grammar and Word Statistics. AAAI-97. Michael Collins, 1997. Three generative, lexicalised models for statistical parsing. ACL/EACL '97.
Weds 3/16	Research paper presentation: Dave Crandall (.pdf)		Paper critiques (2) due. (See 3/7 for associated readings from J&M.) Dan Klein and Christopher D. Manning. Parsing with Treebank Grammars: Empirical Bounds, Theoretical Models, and the Structure of the Penn Treebank. ACL 2001. Steedman et al. 2003. Example Selection for Bootstrapping Statistical Parsers. NAACL '03.
Mon 3/21	NO CLASS: spring break
Weds 3/23	NO CLASS: spring break
Mon 3/28	Semantic representation (.pdf)	J&M Chapter 14
Weds 3/30	Research paper presentation: Justin Hart (paper1.pdf and paper2.pdf)		Paper critiques (2) due. Gildea, D. and Palmer, M. 2002. The Necessity of Parsing for Predicate Argument Recognition, ACL-02. Lev et al., 2004. Solving logic puzzles: From robust processing to precise semantics. ACL Workshop on Text Meaning and Interpretation.
Mon 4/4	Syntax-driven semantic analysis (.pdf)	J&M Chapter 15
Weds 4/6	Research paper presentation: Thomas Womack (.pdf)		Paper critiques (2) due. Gildea, D. and Jurafsky, D. 2000. Automatic Labeling of Semantic Roles. ACL-2000. Pradhan et al., 2004. Shallow Semantic Parsing Using Support Vector Machines. NAACL-HLT 2004.
Fri 4/8	[not a class day]		Project literature survey due.
Mon 4/11	Information extraction (.pdf)
Weds 4/13	Research paper presentation: Dusty Sargent (.pdf) and Warren Wong (.pdf)		Paper critiques (2) due. Hobbs et al., 1996. FASTUS: A Cascaded Finite-State Transducer for Extracting Information from Natural Language Text. In Emmanuel Roche and Yves Schabes (eds.) Finite State Devices for Natural Language Processing. MIT Press. Cardie, C. Empirical Methods in Information Extraction. AI Magazine, 18:4, 65--79 1997.
Mon 4/18	Pragmatics and inference (.pdf)
Weds 4/20	Research paper presentation: Joe Dillman (paper1.pdf and paper2.pdf)		Paper critiques (2) due. Riloff, E., 1996. Automatically Generating Extraction Patterns from Untagged Text. AAAI-96. Riloff, E. and Wiebe, J., 2003. Learning Extraction Patterns for Subjective Expressions. EMNLP-03.
Mon 4/25	Reference resolution (.pdf)	J&M Chapter 18
Weds 4/27	Research paper presentation: Gilly Leshed		Paper critiques (2) due. Ng, V. and Cardie, C. 2002. Improving Machine Learning Approaches to Coreference Resolution. ACL-2002. Strube et al., 2002. The Influence of Minimum Edit Distance on Reference Resolution. EMNLP '02.
Mon 5/2	Question answering
Weds 5/4	Research paper presentation: Pavel Dmitriev		Paper critiques (2) due. Copestake, A. and Lascarides, A. 2002. Integrating Symbolic and Statistical Representations: The Lexicon Pragmatics Interface. ACL-02. Narayanan, S. and Harabagiu, S. 2004. Question Answering based on Semantic Structures. COLING 2004.
Mon 5/9	Schedule		Project presentations.
Tues 5/10	Schedule		Project presentations.
Mon 5/16			Project report due.