Ling7800: Advanced Computational Linguistics: Lexical Semantics

Spring 2007

Time and Location: Tuesday 9:30-10:45 Stadium ITS classroom 308 (gate 7), Thursday 9:30-10:45 Hellems Linguistics Dept Lounge
Assessment: Presentation of two papers, two homeworks and a term project.
Office Hours: Thursday 11:00 - 12:00 and Friday 5-6
Instructor: Martha Palmer

Theme

One of the great challenges of Natural Language Processing is the multitude of choices that language gives us for expressing the same thing in different ways. This is obviously true when taking other languages into consideration - the same thought can be expressed in English, French, Chinese or Russian, with widely varying results. But it is also true when considering a single language such as English. Light verb constructions, nominalizations, idioms, slang, paraphrases, and synonyms all give us myriads of alternatives for "coining a phrase."

With respect to other languages, one solution that has been often touted is that of an "interlingua:" a universal, language neutral semantic representation that all languages could be mapped onto. This approach has an immediate appeal, since it would obviate the need for specific translation systems for every possible pair of languages. Instead, it would only be necessary to build systems for each individual language that can produce the interlingua representation from an analysis of the sentences in the language, and that can generate fluent sentences from interlingua representations. As desirable as this may seem, and in spite of the tremendous effort that has gone into this quest, the realization of a suitable "interlingua" has proven to be elusive.

The students in this course will be encouraged to form their own opinion of the feasibility of an "interlingua." We will explore in depth alternative styles of semantic representations, and compare and contrast their contributions to finding a useful, common semantic representation that can bridge lexical and structural gaps both mono-lingually and multi-lingually. We will look particularly closely at Question Answering and Recognizing Textual Entailments as NLP applications that are in dire need of such bridges. We will also explore alternative styles of semantic annotations and their cross-linguistic application.

Suggested Schedule and Readings - Open to Modification

Introduction and Module 1: the Lexical Semantics of Verbs

Jan 16, 18, 23, 25, 30, Feb 1, 6, 8, 13, 15, 20, 22, 27

Module 2: Semantic Representations in NLP Applications - recent

March 15, April 3, 5

Module 3. Machine Learning

March 20, 22, Dima

Module 4: Word Sense Disambiguation

April 10 (Dima)

Module 5: Ontolgies in NLP

Apr 12 (Also Projects), 17, 19

Module 6: Empirical Studies of Lexical Semantic Phenomena

April 24, 26 - NAACL Conference, No classes
May 1, 3,

Module 7: Additional Reading, Inducing Verb Classes

Module 7: Project Presentations

Final Exam time, Wed, May 9 10:30 - 1:30