CPSC 503 - Winter 2008 -
Computational Linguistics
Readings, Syllabus, Assignments,
Software&Data
|
Syllabus, Assignments, Software& Data
1
Sep 8 M Intro and Course Overview J&M
Chp. 1
- ACL
- NLP demos
-Ambiguity
2
Sep 10W 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 22)
3
Sep 15M Finish FST
Stemming
J&M
Chp. 2&3
- Xerox: FiniteState Technology, Finite State Morphological Analysis , Products
- Finite State Utilities (Van Noord)
- The Porter Stemmer (includes perl implementation)
4
Sep 17W Spelling: Bayesian method and Minimum Edit Distance - Intro to N-grams
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 22M Probabilistic Models: N-grams and
Model Evaluation
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 24W Hidden Markov Models and Part-of-speech Tagging J&M
Chp. 5-6
Assignment2(due Oct 6)
Corpora: wsj-p.txt wsj-ps.txt atis3.pos.tags.txt cmpt-hw2-3.txt
7
Sep 29M English Syntax and Context-free Grammars
J&M
Chp. 12
Interactive tutorials on the English grammar
English Dept. University of Calgary.
8
Oct 1W Parsing Algorithms J&M Chp. 13 - NLTK (demos)
- Some public parsers (inlcuding Stanford and MINIPAR visualization tools)9
Oct 6M Finish Parsing / Chunking / Dependency Grammars J&M Chp. 13 10 Oct 8W
Probabilistic Parsing Algorithms J&M Chp. 14 -Penn Treebank
-Popular Stat Parser11
Oct 15W
Representing Meaning and
Semantic Analysis
J&M Chp. 17-18
12
Oct 20M
Lexical Semantics J&M Chp.19
Assignment3 (due Oct 29) needed files
- Wordnet
- FrameNet
- ProbBank (adding semantic annotations to the Penn Treebank)
13
Oct 22W Computational Lexical Semantics
J&M Chp. 20
- SENSEVAL(Evaluation for WSD)
- Dependency-based word similarity demo
- TREC (Text REtrieval Conference)
- Semantic Labeling (ASSERT)
14
Oct 27M Discourse&Dialog
J&M Chp. 21 & 24
- DAMSL
- RST annotation tool15
Oct 29W Natural Language Generation (NLG)
GEAhandout
- SIGGEN
- NLG systems book
- CoGenTex (NLG company)16 Nov 3M Project Proposal Presentations -
READINGS (what to do?)
17
Nov 5W 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 [Matthew1]
Ryuichiro Higashinaka et al. Learning to generate naturalistic utterances using reviews in spoken dialogue systems Proceeding of ACL 2006 pdf [Patrick]18
Nov 10M 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 [Ivan1]
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) [Hammad1]19
Nov 12W Summarization (2)
Regina Barzilay, Kathleen McKeown "Sentence Fusion for Multidocument News Summarization",
Computational Linguistics, 2005. [ps] [KK]
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 [Bruno]20
Nov 17M Summarization(3)
Gabriel Murray and Giuseppe Carenini Summarizing Spoken and Written Conversations EMNLP 2008 [pdf] [Shafiq1][new] Giuseppe Carenini , Raymond NG, Xiaodong Zhou, Summarizing Emails with Conversational Cohesion and Subjectivity ACL 2008 [pdf] [Shafiq2]
Gabriel Murray and Giuseppe Carenini Summarizing Spoken and Written Conversations: A Study in Domain Adaptation (Draft 2008 - will be distributed by email)
21
Nov 19W 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. [Hammad2]
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. [Anseok]
22
Nov 24M Natural Language Generation (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 [Ivan2]
Rashmi Prasad, Aravind Joshi, Nikhil Dinesh, Alan Lee, Eleni Miltsakaki, and Bonnie Webber The Penn Discourse TreeBank as a Resource for Natural Language Generation Proceedings of the Corpus Linguistics Workshop on Using Corpora for Natural Language Generation, Birmingham, U.K. July 2005. [Matthew2]
23 Nov 26W Project Update Presentations 24
Dec
8-12Project Final Presentations