CSE 507 Computational Linguistics

Spring 2012

Tue / Thu 3:50pm - 5:10pm at [CS-2114]

Instructor:

Yejin Choi

Office Hours: Tue/Thu 5:10pm - 6:10pm

Announcements:

There will be no class on Feb 7 (instructor out of town)
Project proposal due Feb 29 11:59pm (submit to Blackboard)
Project update due Apr 5 11:59pm (submit to Blackboard)

Course Description:

This course intends to provide a general introduction to Computational Linguistics, the study of computational systems to understand and/or generate human language. This class will cover fundamental concepts and techniques in Computational Linguistics, such as lexical semantics, word sense disambiguation, semantic parsing, discourse (including coreference resolution), dialog, summarization, generation. Throughout the class, students will be exposed to some of the recent research papers that connect the concepts learned from the textbook to exciting research questions that are practically motivated.
Textbook: Jurafsky and Martin, SPEECH and LANGUAGE PROCESSING: An Introduction to Natural Language Processing, Computational Linguistics, and Speech Recognition , Second Edition, McGraw Hill, 2008.

Prerequisites: Familiarity with either Artificial Intelligence or Machine Learning is strongly recommended, but not strictly necessary.

Tentative Grading:

- One must attend at least 75% of all sessions. (Total number of sessions is TBD.) Everyone must actively participate in each session. You can either make a comment, or ask a question, or answer a question --- you must do at least one of the three in each session, but desirably much more than the minimum requirement. Submit the written critique at the beginning of each session as a print-out. It is recommended that you will bring a printed copy of the paper to the class. You will receive a penalty in your score if you walk in late for the paper discussion. You cannot submit your critique after the session. There will be no student paper presentation.

Late submission: Each student may adjust his/her homework deadline upto 7 days throughout the semester without a penalty. (not 7 days for each assignment, but 7 days cumulatively for the entire semester). After then, 10% of score will be subtracted each day. This rule does not apply to the critique submission which is due at the beginning of the class for the paper discussions. If you're late, then it is considered to be that you decided to skip the corresponding session. This policy is to encourage students to submit quality work, rather than poorly composed work in a hurry. For the purpose of counting late submission, factional values will be rounded up - for instance, late submission by 1 hour is counted as late by 1 day. If there are situations where the application of this rule can be ambiguous, I have the right to apply the rule as I see appropriate. If you have a doubt, consult with me first before making your own assumption.

Assignments are posted to Blackboard

Tentative Syllabus: (subject to change depending on the students' backgrounds and interests)

	Date	Topics	Paper Critique Assignment
--- Slides (provided below for convenience) correspond to roughly 70% of the actual class material. The rest will be delivered on the chalkboard. For future lectures, slides from the last year's class are provided for now. Some of these slides may get updated after the lecture. Updated slides will be clearly marked. ---
01	Tue Jan 24	Introduction (See Blackboard for slides)
02	Thu Jan 26	Lexical Semantics & WordNet [slides]
03	Tue Jan 31	Word Sense Disambiguation (WSD) [slides]
04	Thu Feb 02	Word Sense Disambiguation (WSD) [slides] & Selectional Preference [slides]	(1) How opinions are received by online communities: A case study on Amazon.com helpfulness votes. Cristian Danescu-Niculescu-Mizil and Gueorgi Kossinets and Jon Kleinberg and Lillian Lee. Proceedings of WWW, pp. 141--150, 2009.
05	Tue Feb 07	No Class
06	Thu Feb 09	Lexical Similarity & Vector Space Model [slides]	(2) Learning General Connotation of Words using Graph-based Algorithms. Song Feng, Ritwik Bose, and Yejin Choi. Empirical Methods in Natural Language Processing (EMNLP), 2011.
07	Tue Feb 14	Lexical Similarity & Vector Space Model [slides] Click [here] for the WWW 2010 paper slides shown in the class.
8	Thu Feb 16	Machine Learning 101 [slides]	(3) Unsupervised Large-Vocabulary Word Sense Disambiguation with Graph-based Algorithms for Sequence Data Labeling. Rada Mihalcea, EMNLP 2005
9	Tue Feb 21	Project suggestions (See blackboard for slides) Machine Learning 101 [slides]
10	Thu Feb 23	Thematic Roles & PropBank & FrameNet [slides]	(4) Glen, Glenda or Glendale: Unsupervised and Semi-supervised Learning of English Noun Gender. Shane Bergsma, Dekang Lin, Randy Goebel, CoNLL, 2009.
11	Tue Feb 28	Thematic Roles & PropBank & FrameNet [slides]
12	Thu Mar 01	Semantic Role Labeling [slides]	(5) Rajesh Ranganath, Dan Jurafsky, and Dan McFarland. 2009. It's Not You, it's Me: Detecting Flirting and its Misperception in Speed-Dates. Proceedings of EMNLP 2009.
13	Tue Mar 06	Grammar Formalism: CFG [slides]
14	Thu Mar 08	Grammar Formalism: Features & Unification [slides]	(6) Greene, Stephan and Philip Resnik, "More than Words: Syntactic Packaging and Implicit Sentiment", Proceedings of Human Language Technologies: The 2009 Annual Conference of the North American Chapter of the Association for Computational Linguistics June, 2009,
15	Tue Mar 13	Grammar Formalism: Beyond CFG [slides]
16	Thu Mar 15	Grammar Formalism: Beyond CFG [slides]	(7) David K. Elson, Nicholas Dames, Kathleen R. McKeown. Extracting Social Networks from Literary Fiction. ACL 2010 (Best Student Paper Award)
17	Tue Mar 20	Grammar Formalism: CCG & TAG [slides]
18	Thu Mar 22	Discourse: Coreference (Anaphora) Resolution [slides]
19	Tue Mar 27	Project Update Presentations I
20	Thu Mar 29	Project Update Presentations II
21	Tue Apr 03	No Class (Spring Break)
22	Thu Apr 05	No Class (Spring Break)
23	Tue Apr 10	Discourse: Coreference (Anaphora) Resolution [slides]
24	Thu Apr 12	Discourse: Text Coherence & Rhetorical Structure Theory [slides]
25	Tue Apr 17	Discourse: Text Coherence & Rhetorical Structure Theory [slides]	(8) Modeling Local Coherence: An Entity-based Approach. Regina Barzilay, and Mirella Lapata, ACL 2005
26	Thu Apr 19	Discourse: Segmentation [slides] & Coreference (Anaphora) Resolution Intro [slides]
27	Tue Apr 24	Hypothesis Testing I [slides]
28	Thu Apr 26	Hypothesis Testing II [slides] + project discussion
29	Tue May 01	Question Answering & Textual Inference
30	Thu May 03	Final Project Presentation I & II