CPSC 503 - Spring 2005 -
Computational Linguistics
Readings, Syllabus, Assignments,
Software&Data
|
1
Jan 13 (Th) Intro and Course Overview J&M Chp. 1
- ACL
- NLP demos
-Ambiguity
2
Jan 18 (Tu) English Morphology Finite State Transducers (1)
J&M Chp. 2&3
Applications of FSTs in NLP Lauri Karttunen, CIAA, 2000. 3
Jan 20 (Th) English Morphology Finite State Transducers (2) J&M Chp. 2&3
- Xerox: FiniteState Technology, Finite State Morphological Analysis , Products
- Finite State Utilities (Van Noord)
- AT&T FSmachines toolkit
- The Porter Stemmer (includes perl implementation)
4
Jan 25 (Tu) Spelling: Bayesian method and Minimum Edit Distance - Intro to n-grams
J&M Chp. 5 (141-156) - min-edit-dist demo
- A spelling correction program based on a noisy channel model Kerninghan et al. COLING ,1990.5
Jan 27 (Th) Probabilistic Models: n-grams
Model Evaluation and Hidden Markov Models(1)
J&M Chp. 6
M&S Chp. 9An empirical study of smoothing techniques for NLP S.F. Chen, J. Goodman - TR CS Harvard Univ - 1998
6
Feb 1 (Tu) Hidden Markov Models(2) and Part-of-speech Tagging M&S Chp. 9
J&M Chp. 8Assignment2
7
Feb 3 (Th) English Syntax and Context-free Grammars
J&M Chp. 9
8
Feb 8 (Tu) Parsing Algorithms J&M Chp. 10 NLTK (demos) 9
Feb 10 (Th) Probabilistic Parsing Algorithms J&M Chp. 12 Penn Treebank
Popular Stat Parser
Feb 14-18 spring break week
10 Feb 22 (Tu) Representing Meaning
J&M Chp. 14 ProbBank (adding semantic annotations to the Penn Treebank)
11
Feb 24 (Th) Semantic Analysis
J&M Chp. 15 Assignment3 12
Mar 1 (Tu) Lexical Semantics J&M Chp. 16 Wordnet
FrameNet13
Mar 3 (Th) Word Sense Disambiguation (WSD) and Information retrieval (IR)
J&M Chp. 17 SENSEVAL(Evaluation for WSD)
TREC (Text REtrieval Conference)
14
Mar 8 (Tu) Discourse&Dialog J&M Chp. 18-19 DAMSL
RST annotation tool
15
Mar 10 (Th) Natural Language Generation (NLG) J&M Chp. 20 SIGGEN
NLG systems book
16
Mar 15 (Tu) Project Proposal Presentations
17
Mar 17 (Th) NLG evaluation
(Jenninfer, Terry)
- E Reiter, R Robertson, and LM Osman (2003). Lessons from a Failure: Generating Tailored Smoking Cessation Letters. Artificial Intelligence 144:41-58. (PDF) ...for more info on STOP system
- Walker, M., Whittaker, S., Stent, A., Maloor, P., Moore, J., Johnston, M., Vasireddy, V. (2004). Generation and Evaluation of User Tailored Responses in Dialogue. Cognitive Science, 28, (PDF)
18
Mar 22 (Tu) Semantic Term Similarity
- Resnik, P. (1999) "Semantic Similarity in a Taxonomy: An Information-Based Measure and its Application to Problems of Ambiguity in Natural Language", Journal of Artificial Intelligence Research (JAIR) Volume 11, pages 95-130. resnik99a.pdf
(Lyndon, Flavio)
- Dagan, Ido. Contextual Word Similarity, in Rob Dale, Hermann Moisl and Harold Somers (Eds.), Handbook of Natural Language Processing, Marcel Dekker Inc, 2000, Chapter 19, pp. 459-476.
19
Mar 24 (Th) Extracting Subjective Info
(Maryam, Sara)
- Theresa Wilson, Janyce Wiebe, and Rebecca Hwa (2004). Just how mad are you? Finding strong and weak opinion clauses. Proceedings of the Nineteenth National Conference on Artificial Intelligence (AAAI). (pdf)
- Hong Yu and Vasileios Hatzivassiloglou, Towards Answering Opinion Questions: Separating Facts from Opinions and Identifying the Polarity of Opinion Sentences, Empirical Methods in Natural Language Processing
(EMNLP 2003) (pdf)
20
Mar 29 (Tu) Summarization
- Regina Barzilay & Michael Elhadad ``Using Lexical Chains for Text Summarization'', in Advances in Automatic Text Summarization, Chapter 10, I. Mani and M.T. Maybury eds, MIT Press, 1999 (revised and expanded version of the paper in Intelligent Scalable Text Summarization Workshop (ISTS'97), ACL, Madrid, 1997) (copy in reading room)
(Adam)
(Biographies) Zhou, Liang; Ticrea, Miruna; Hovy, Eduard, Multi-document Biography Summarization, Proceedings of EMNLP, pp. 434-441, 2004 (pdf)
21
Mar 31 (Th) Acquisiton of knowledge sources for NLG
- Srinivas Bangalore and Owen Rambow, Corpus-Based Lexical Choice in Natural Language Generation, Association of Computational Linguistics (ACL 2000) , Hongkong, China, October 2000.
- Pablo A. Duboue and Kathleen R. McKeown, Statistical Acquisition of Content Selection Rules for Natural Language Generation, in Proceedings of the 2003 Conference on Empirical Methods for Natural Language Processing (EMNLP 2003), July 2003, Sapporo, Japan.
( Jennifer, Terry)
22
Apr 5 (Tu) Acquisiton of knowledge sources for NLG
<>
> - Marilyn A. Walker, Owen C. Rambow and Monica Rogati, Training a sentence planner for spoken dialogue using boosting, Computer Speech and Language Volume 16, Issues 3-4, Pages 409-433 (July - October 2002)
(Maryam, Sara)
23
Apr 7 (Th) Project Update Presentations
Apr .... Project Final Presentations