CPSC 503 - Winter 2009 -
Computational Linguistics
Readings, Syllabus, Assignments,
Software&Data
|
Syllabus, Assignments, Software& Data
1
Sep 9 W Intro and Course Overview subscribe to course mailing list - send a message to majordomo@cs.ubc.ca with body: subscribe cpsc503
J&M
Chp. 1
- ACL
- NLP demos
-Ambiguity
2
Sep 11F English Morphology and Finite State Machines: FSA and FST
J&M
Chp. 2&3
Applications of FSTs in NLP Lauri Karttunen, CIAA, 2000.
Assignment1 (due Sep 18)
3
Sep 16W Finish FST
Stemming
J&M
Chp. 2&3
- Recent book and software
- Xerox: FiniteState Technology, Finite State Morphological Analysis
- Finite State Utilities (Van Noord)
- The Porter Stemmer (includes perl implementation)
4
Sep 18F Spelling: Bayesian method and Minimum Edit Distance
J&M
Chp. 3&4
- ProbInfoTheory Handout
- min-edit-dist demo
- A spelling correction program based on a noisy channel model Kerninghan et al. COLING ,1990.
- minimal Python implementation of spelling correction (by P. Norvig)
5
Sep 23W Probabilistic Models: N-grams
J&M
Chp. 4
Google ngrams model An empirical study of smoothing techniques for NLP S.F. Chen, J. Goodman - TR CS Harvard Univ - 1998
6
Sep 25 F Smoothing - Model Evaluation - Intro Markov Models J&M
Chp. 4-57
Sep 30W Hidden Markov Models and Part-of-speech Tagging J&M
Chp. 5-6
why tagging can be challenging for humans: Penn tagging scheme Assignment2(due Oct 14)
Corpora: wsj-p.txt wsj-ps.txt atis3.pos.tags.txt cmpt-hw2-3.txt
8
Oct 2 F English Syntax and Context-free Grammars
J&M
Chp. 12
Interactive tutorials on the English grammar
English Dept. University of Calgary.
9
Oct 7 W Parsing Algorithms J&M Chp. 13 - NLTK (demos)
- Some public parsers (inlcuding Stanford and MINIPAR visualization tools)10 Oct 9 F
Finish Parsing / Chunking / Dependency Grammars J&M Chp. 13 11
Oct 14W
Probabilistic CFGs J&M Chp. 14 -Penn Treebank - Stanford Parser -
-Popular Stat Parser12
Oct 16 F Representing Meaning and
Semantic Analysis
J&M Chp. 17-18 Assignment3 (out Oct 20- due Oct 30) needed files
13
Oct 21W Lexical Semantics J&M Chp.19
- Wordnet
- FrameNet
- ProbBank (adding semantic annotations to the Penn Treebank)
14
Oct 23F Computational Lexical Semantics
J&M Chp. 20
- SENSEVAL(Evaluation for WSD)
- Dependency-based word similarity demo
- TREC (Text REtrieval Conference)
- Semantic Labeling (ASSERT)
15
Oct 28W Discourse&Dialog
J&M Chp. 21 & 24
- DAMSL
- RST annotation tool16 Oct 30 F Natural Language Generation (NLG)
GEAhandout
- SIGGEN
- NLG systems book
- CoGenTex (NLG company)17
Nov 4 W Project Proposal Presentations - READINGS (what to do?)
18
Nov 6 F Natural Language Generation (1)
E Reiter, R Robertson, and LM Osman . Lessons from a Failure: Generating Tailored Smoking Cessation Letters. Artificial Intelligence 144:41-58. (2003)(pdf) ...for more info on STOP system [Nicholas]
Ryuichiro Higashinaka et al. Learning to generate naturalistic utterances using reviews in spoken dialogue systems Proceeding of ACL 2006 pdf [Andrew]19
Nov 11W Holiday - Remembrance Day 20
Nov 13F Summarization (1)
(Biographies) Fadi Biadsy, Julia Hirschberg, Elena Filatova, "An Unsupervised Approach to Biography Production using Wikipedia", ACL-08: HLT, Columbus, Ohio, Jun 2008 pdf [Jiarui]
Lin, Chin-Yew and E.H. Hovy. Automatic Evaluation of Summaries Using N-gram Co-occurrence Statistics. In Proceedings of Language Technology Conference (HLT-NAACL ), 2003. (pdf) [Arseniy]21
Nov 18W Summarization (2)
Regina Barzilay, Kathleen McKeown "Sentence Fusion for Multidocument News Summarization",
Computational Linguistics, 2005. [ps] [Alexander]
Ani Nenkova et al. The Pyramid Method: Incorporating human content selection variation in summarization evaluation ACM Trans. on Speech and Language Processing (TSLP), 2007 pdf [Sophie]22
Nov 20F Summarization(3)
Gabriel Murray and Giuseppe Carenini Summarizing Spoken and Written Conversations EMNLP 2008 [pdf] [Jiarui]Giuseppe Carenini , Raymond NG, Xiaodong Zhou, Summarizing Emails with Conversational Cohesion and Subjectivity ACL 2008 [pdf] [Arseniy]
23 Nov 25W Info Extraction from Evaluative Text (1)
Theresa Wilson, Janyce Wiebe and Rebecca Hwa (2006). Recognizing strong and weak opinion clauses. Computational Intelligence, 22 (2), pp. 73-99. [John]Theresa Wilson, Janyce Wiebe and Paul Hoffmann (2005). Recognizing Contextual Polarity in Phrase-Level Sentiment Analysis. Proceedings of Human Language Technologies Conference/Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP 2005), Vancouver, Canada. [Shama]
24 Nov 27F Natural Language Generation / Question-Answering (2)
A. Stent, R. Prasad and M. Walker. Trainable sentence planning for complex information presentations in spoken dialog systems. In Proceedings of ACL , 2004. pdf [Shama]
Y. Chali, S. R. Joty and S. A. Hasan (2009) "Complex Question Answering: Unsupervised Learning Approaches and Experiments", Volume 35, pages 1-47, 2009 pdf [Byron]
25 Dec 2 W Project Update Presentations 26
Dec
....Project Final Presentations