INLS 512_001 Fall 2006 Schedule

Schedule

Applications of Natural Language Processing INLS 512_001, Fall 2006

Notes:
This tentative schedule lists the assignments and readings for each of the topics we'll cover. There is no textbook for this class. Readings are mostly available online, but I have also put some useful books on reserve in the SILS library, including a textbook (see the Resources page).

Each reading is marked with its location.

[e-reserves] Online reserves.
[e-journal] Electronic journals are available through the UNC-CH library e-journal list.
[ACM DL] Journals in the ACM Digital Library are available through the UNC-CH library e-journal list, or you can purchase your own subscription.
[ACL] Articles published by the Association for Computational Linguistics may be reached through the ACL Anthology.
[e-book] Readings from electronic books are available through netLibrary, or from a link in their records in the UNC library catalogue.
[web] Articles on the web.
[SILS PAM] Photocopied articles are in the SILS library. PAM boxes are on the far side of the low bookcase in front of the reference desk.
[SILS book] Reserve books are behind the reference desk in the SILS library.

Other readings or assignments may be assigned as appropriate.

Thursday, 8/24/06: Introduction and overview.

Demo: TAPorware wordplay.

Tuesday, 8/29/06: Introduction, cont.

Crane, G. & Jones, A. (2006). The challenge of virginia banks: An evaluation of named entity analysis in a 10th-century newspaper collection. Proceedings of JCDL '06, 31-40. [ACM DL]
Popescu, A-M. & Etzioni, O. (2005). Extracting product features and opinions from reviews. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), 339-346. [ACL]
read sections 1-3.3.3; skim 3.3.4-3.3.7; read 3.4-end

Thursday, 8/31/06: Language, software, and corpora

Fellbaum, C. (1998). Introduction. In Fellbaum, C. (ed). (1998). WordNet: An Electronic Lexical Database MIT Press, 1-19. [e-reserves] [SILS book, SILS P325.5.D38 W67 1998]
Miller, G. (1998). Nouns in WordNet. In Fellbaum, C. (ed). (1998). WordNet: An Electronic Lexical Database MIT Press, 23-46. [e-reserves] [SILS book, SILS P325.5.D38 W67 1998]
Demo: WordNet
Download and install GATE. As the semester goes on, you may wish/need to download other tools as well.

Tuesday, 9/5/06: Language, software, corpora, cont.

Thompson, H. (2000). Corpus creation for data-intensive linguistics. In R. Dale, H. Moisl & H. Somers (eds.). Handbook of Natural Language Processing, Ch. 16, 385-401. [e-book]
Demo: Linguistic Data Consortium, British National Corpus, other corpora.

Thursday, 9/7/06: Tokenisation and sentence identification.

Palmer, D. (2000). Tokenisation and sentence segmentation. In R. Dale, H. Moisl & H. Somers (eds.). Handbook of Natural Language Processing, Ch. 2, 11-35. [e-book]
Mikheev, A. (2003). Text segmentation. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 10, 201-218. [e-reserves] [SILS book, P98 .O95 2003]

Tuesday, 9/12/06: Tokenisation and sentence identification, cont.

Start Exercise 1: Tokens and sentences in class. Due Thursday, 9/14/06.

Thursday 9/14/06: Part of speech tagging.

Sproat, R. (2000). Lexical Analysis. In R. Dale, H. Moisl & H. Somers (eds.). Handbook of Natural Language Processing, Ch. 3, 37-57. [e-book]
read section 1, skim the first part of section 3, skim 4, read 5, skim 7 & 8
Voutilainen, A. (2003). Part-of-Speech Tagging. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 11, 219-232. [e-reserves] [PAM] [SILS book, P98 .O95 2003] recommended
Brill, E. (1992). A simple rule-based part of speech tagger. Proceedings of the Third Conference on Applied Natural Language Processing, 152-155. highly recommended
POS slides
A list of the Penn Treebank Word Level Tags
Exercise 1 due.

Tuesday, 9/19/06: POS tagging, cont.

Start Exercise 2: Part of speech tagging in class. Due Tuesday, 9/26/06.

Thursday, 9/21/06: Happy 75th Birthday to SILS! No class today.
Please attend the Student Day events.

Tuesday, 9/26/06: Sentence structure, grammars, and parsers.

The Penn TreeBank Tagset
Exercise 2 due.
Slides for this section.

Thursday, 9/28/06: Grammars & parsers, cont.

Ramshaw, L. & Marcus, M. (1995). Text chunking using transformation-based learning. Proceedings of the Third ACL Workshop on Very Large Corpora, 82-94. [ACL]
Demo: Visual Interactive Syntax Learning (VISL)

Tuesday, 10/3/06: Grammars and Parsing, cont.

Start Exercise 3: Parsing in class, due Thursday, 10/5/06.

Thursday, 10/5/06: Information Extraction

Cowie, J. & Wilks, Y. (2000). Information Extraction. In R. Dale, H. Moisl & H. Somers (eds.). Handbook of Natural Language Processing, Ch. 10, 241-260. [e-book]
Grishman, R. (2003). Information Extraction. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 30, 545-559. [e-reserves] [SILS book, P98 .O95 2003]
Introduction to Information Extraction, from the National Institute of Standards and Technology (NIST), which runs MUC, TREC, DUC, and other such conferences. [web]
What is Information Extraction?, including the examples. [web]
MUC-6. Skim the rules and look at the scores to see what performance was like in 1995. [web] skim
Chincor, N. (1996). Overview of MUC-7 gives a brief history of MUC and description of the tasks. [web] recommended
Exercise 3 due.
Discuss final projects or papers.

Tuesday, 10/10/06: Information extraction, cont.

Mitkov, R. (2003). Anaphora Resolution. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 14, 266-283. [e-reserves] [SILS book, P98 .O95 2003] skim
The ACE 2006 (ACE06) Evaluation Plan describes the tasks of the current evaluation conference. [web] skim
The Automatic Content Extraction (ACE) homepage. [web] skim
Ahn, D. (2006). The stages of event extraction. Proceedings of the Workshop on Annotating and Reasoning about Time and Events, 1-8. This is an example of an ACE application. [ACL]
Jacqeumin, C. & Bush, C. (2000). Combining lexical and formatting cues for named entity acquisition from the Web. Joint SIGDAT Workshop on Empirical Methods in NLP and Very Large Corpora, 181-189. [ACL]
Minkov, E., Wang, R. & Cohen, W. (2005). Extracting personal names from email: Applying named entity recognition to informal text. Proceedings of Human Language Technology Conference and Conference on Empirical Methods in Natural Language Processing (HLT/EMNLP), 443-450. [ACL]
Assign GATE assignment, due Thursday, 11/3/06.

Thursday, 10/12/06: University Day, no class.

Tuesday, 10/17/06: Information extraction, cont.

Start Exercise 4: Named entity identification in class, due Tuesday, 10/24/06.

Thursday, 10/19/06: Fall Break, no class.

Tuesday, 10/24/06: Summarization

Mani, I. (2001). Automatic Summarization. Amsterdam: John Benjamins Publishing Co.
- Chapter 1, Preliminaries, 1-25. [e-reserve]
- Chapter 7, Multi-document summarization, 169-220. [e-reserve]
Moens, M. (2000). Automatic Indexing and Abstracting of Document Texts. Boston; Kluwer Academic Publishers.
- Ch. 7, Text structuring and categorization when summarizing legal cases, 157-172. [e-reserve]
- Ch. 8, Clustering of paragraphs when summarizing legal cases, 173-190. [e-reserve]
Radev, D. et al. (2003). Experiments in single and multi-document summarization using MEAD. Proceedings of the Document Understanding Conference Workshop on Summarization. [web]
The Document Understanding Conference (DUC) homepage. [web] skim
Demo: NewsInEssence, MEAD
MEAD demo results
Exercise 4 due today.

Thursday, 10/26/06: Summarization, cont.

Start Exercise 5: Summarization in class, due Tuesday, 10/31/06.

Tuesday, 10/31/06: Sublanguage and genre

Kittredge, R. (2003). Sublanguages and controlled languages. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 23, 430-447. [e-reserves] [SILS book, P98 .O95 2003]
Travers, D. & Haas, S. (2003). Using nurses' natural language entries to build a concept-oriented terminology for patients' chief complaints in the emergency department. Journal of Biomedical Informatics, 36(4-5), 260-270. [e-journal]
Haas, S. & Travers, D. (2004). Issues in the development of a thesaurus for patients' chief complaints in the hospital emergency department. Proceedings of the 2004 Annual Meeting of the American Society for Information Science and Technology, 411-417. [e-reserves]
Slides for this week.
Exercise 5 due.
Project proposals due.

Thursday, 11/2/06: Sublanguage and genre, cont.

Swales, J. (1990). Genre Analysis. Cambridge University Press. Ch. 3, The concept of genre, 33-67. [e-reserves]
Crowston, K. & Kwasnik, B. (2004). A framework for creating a facetted classification for genre: Addressing issues of multidimensionality. Proceedings of the 37th Hawaii international Conference on System Sciences, p. 40100a, track 4. [web]
GATE assignment due.

Tuesday, 11/7/06: Sentiment identification

Hatzivassiloglou, V. , Weibe, J. (2000). Effects of adjective orientation and gradability on sentence subjectivity. Proceedings of COLING, 299-305.
Pan, B., Lee, L & Vaithyanathan, S. (2002). Thumbs up? Sentiment classification using machine learning techniques. Proceedings of the Workshop on Empirical Methods in Natural Language Processing (EMNLP), 79-86.

Thursday, 11/9/06: Machine translation.

Somers, H. (2000). Machine translation. In R. Dale, H. Moisl & H. Somers (eds.). Handbook of Natural Language Processing, Ch. 13, 329-346. [e-book]
Hutchins, J. (2003) Machine translation: General overview. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 27, 501-511. [e-reserves] [SILS book, P98 .O95 2003]
Somers, H. (2003). Machine translation: Latest developments. In R. Mitkov (ed.) The Oxford Handbook of Computational Linguistics. Oxford University Press. Ch. 28, 512-528. [e-reserves] [SILS book, P98 .O95 2003]
Demo: back translation
Slides for today.

Tuesday, 11/14/06: MT cont.: Cross-Language Information Retrieval

Thursday, 11/16/06: Generation

McKeown, K., et al. (1997). Language Generation for Multimedia Healthcare Briefings Fifth Conference on Applied Natural Language Processing, 277-282. [ACL DL]
Stoia, L. et al. (2006). Noun Phrase Generation for Situated Dialogs Proceedings of the Fourth International Natural Language Generation Conference, 81-88. [ACL DL]
Slides for today.

Tuesday, 11/21/06: Spoken Dialogue Systems and Chatterbots

Walker, M. et al. (2000). Learning to predict problematic situations in a spoken dialogue system: Experiments with How May I Help You? Proceedings of the First Meeting of the North American Chapter of the Association for Computational Linguistics, 210-217. [ACL DL]
Look at the Loebner Prize Website. Suggestions: the rules for the 2007 competition, and some transcripts from previous winners. (Scroll down to the bottom of the page.)
Play with a couple of chatterbots. See the bottom of the Resources page for links.

Thursday, 11/23/06: Thanksgiving, no class.

Tuesday, 11/28/06: Wrap-up: Future applications of NLP. Course evaluation.

Thursday, 11/30/06: Poster session

Presentations: Paul Greitzer, Tyler Kendall, Genya O'gara, Joshua Vossler.

Tuesday, 12/5/06: Poster session

Presentations: Anna Craft, Philip Fulcher, Martina Gargard, Ann Irvine.

Tuesday, 12/12/06, 12:00 noon: Final papers due.

Return to the top of the page.

This page was last modified on August 16, 2006, by Stephanie W. Haas. Address questions and comments about this page to Stephanie W. Haas: stephani at ils dot unc dot edu
© Stephanie W. Haas, 2006 All rights reserved.