Linguistics 580G: Statistical Methods in NLP

Course Info

• Lecture: Th 3:30-5:50, MGH 254
• Texts: Most of the papers we will be reading this quarter are available electronically (see the links in the schedule of topics & assignments). Others will be made available through course reserves. In addition, I've requested that Manning & Schutze 1999 (second printing 2000) and Jelinek 1997 be placed on reserve in Odegaarde.
• Our EPost bulletin board (Instructions on using EPost)

Instructor Info

• Emily M. Bender
• Office Hours: Thursday 1-3 & by appt
• Office: Padelford B-201
• Phone: 616-4963
• Email: ebender at u

Syllabus

Description

The goals of this course are (1) to learn about various statistical methods commonly used in NLP and (2) to explore the ways in which those methods have been applied to various linguistic problems.

Note: To request academic accommodations due to a disability, please contact Disabled Student Services, 448 Schmitz, 206-543-8924 (V/TTY). If you have a letter from Disabled Student Services indicating that you have a disability which requires academic accommodations, please present the letter to the instructor so we can discuss the accommodations you might need in this class.

Requirements

Students will be expected to present some number of papers over the course of the quarter (TBD based on the number of students in the course!), to do all of the assigned readings and participate in the discussion, and to complete a final paper or project. Final papers (of 15-20 pages) could take the form of comparing various approaches to a given linguistic problem (e.g., POS tagging) in the literature. Final projects involve the application of a statistical method to some linguistic problem, and should be accompanied by a short (5 page) write up. Students are encouraged to select topics for either sort of final early, and to discuss them with the instructor.

List of readings

• Abney, Steven P. 1997. Stochastic Attribute-Value Grammars. Computational Linguistics 23(4):597-618.
• Baldwin, Timothy and Francis Bond. 2003a. Learning the Countability of English Nouns from Corpus Data. ACL'03 pp.463-470.
• Baldwin, Timothy and Francis Bond. 2003b. A Plethora of Methods for Learning English Countability. EMNLP'03 pp.73-80..
• Briscoe, E. and J. Carroll. 2002. Robust Accurate Statistical Annotation of General Text. LREC'02.
• Chen, Stanley F. and Joshua Goodman. 1996. An Empirical Study of Smoothing Techniques for Language Modeling. ACL'96:310-318.
• Daelemans, Walter, Jakub Zavrel, Peter Berck and Steve Gillis. 1996. MBT: A Memory-Based Part of Speech Tagger-Generator. Proceedings of the Fourth Workshop on Very Large Corpora. pp.14-27.
• Dagan, Ido, Lillian Lee and Fernando Pereira. 1997. Similarity-based methods for word sense disambiguation. ACL'97. pp.56-63.
• DeRose, Steven J. 1988. Grammatical category disambiguation by statistical optimization. Computational Linguistics 14(1):31-39.
• Elworthy, David. 1995. Tagset Design and Inflected Languages. EACL SIGDAT workshop "From Texts to Tags: Issues in Multilingual Language Analysis".
• Gamon, Michael, Eric Ringger, Robert Moore, Simon Corston-Oliver, and Zhu Zhang. 2002. Extraposition: A case study in German sentence realization. Coling 2002 pp.301-307.
• Johnson, Mark, Stuart Canon, Zhiyi Chi and Stefan Riezler. 1999. Estimators for stochastic 'unification-based' grammars. ACL'99. pp.535-541.
• Jurafsky, Daniel. 1996. A Probabilistic Model of Lexical and Syntactic Access to Disambiguation. Cognitive Science 20(2):137-194. [Available through UW libraries E-Journals]
• Kempe, Andre. 1997. Finite-state transducers approximating hidden markov models. ACL'97:460-467.
• Klein, Dan and Manning, Christopher D. 2003. A* Parsing: Fast Exact Viterbi Parse Selection. Proceedings of HLT-NAACL'03.
• Lesher, G.W, B.J. Moulton and D.J. Higginbotham. 1991. Effects of ngram order and training text size on word prediction. Proceedings of the RESNA '99 Annual Conference. Arlington, CA: RESNA Press. Pp.52-54.
• Mays, Eric, Fred J. Damerau and Robert L. Mercer. 1991. Context Based Spelling Correction. Information Processing and Management: An International Journal. 27(5):517-522.
• Manning, Christopher D. and Hinrich Schutze. 2000. Foundations of Statistical Natural Language Processing MIT Press. Chapters 2.1, 2.2, 9.1-3.
• Nagata, Masaaki and Tsuyoshi Morimoto. 1994. First steps towards statistical modeling of dialogue to predict the speech act type of the next utterance. Selected papers presented at the international symposium on spoken dialogue. pp.193-203.
• Palmer, David D. and Marti A. Hearst. 1997. Adaptive Multilingual Sentence Boundary Disambiguation. Computational Linguistics 23(2):241-267.
• Ratnaparkhi, Adwait. 1996. A Maximum Entropy Part-Of-Speech Tagger. EMNLP'96
• Samuelsson, Christer and Wolfgang Reichl. 1999. A class-based language model for large-vocabulary speech recognition extracted from part-of-speech statistics. Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing, Volume 1. IEEE.pp.537-540.
• Toutanova, Kristina, Christopher D. Manning and Stephan Oepen. 2002. Parse Ranking for a Rich HPSG Grammar. TLT 2002
• Wu, Andi. 2003. Learning Verb-Noun Relations to Improve Parsing. Proceedings of the Second SIGHAN Workshop on Chinese Language Processing.
• Zhou, Guodong and Jian Su. 2002. Named Entity Recognition using an HMM-based Chunk Tagger

Schedule of Topics and Assignments (may be updated)