CS 775: Seminar in Natural Language Understanding

Meetings: (approximately) alternate Wednesdays, 4-5 pm, Upson 5130
Occasionally co-meeting with CS772, the Artifical Intelligence Seminar
Resources: NLP at CUCS | CS674 | Other CS course web pages | Cognitive studies talks

• Feb 11: (cognitive studies colloquium) Tom Mitchell, CMU: The Role of Unlabeled Data in Supervised Learning.
  Phillips 101, 3:15 pm

• Feb 16: discussion of Dan Roth's Learning in Natural Language, IJCAI '99.

• Mar 1: discussion of Greg Keim et al's PROVERB: The Probabilistic Cruciverbalist

• Mar 15: Regina Barzilay, Columbia: Multidocument summarization based on information fusion.

  Abstract: Different on-line documents on the same subject frequently contain substantially similar information. Hence, summaries that synthesize common information across documents and emphasize the differences between them would significantly help readers. In the talk, I will present MultiGen, a summarization system developed at Columbia University, which generates a concise summary of news articles presenting different descriptions of the same event. During the analysis stage, MultiGen identifies repeated information in the input articles; through this process it selects phrases that adequately convey the common information. The generation component orders those phrases and combines them into a fluent summary.

  Aside from MultiGen, I will give a brief overview of automatic summarization, covering genres of summary, techniques for automated summarization, and evaluation strategies.

• Apr 17: Vincent Ng will be giving a practice ANLP talk on "Examining the role of statistical and linguistic knowledge sources in a general question-answering system" (joint work with Claire Cardie, Dave Pierce, and Chris Buckley). Note: just for today, we'll be meeting in Upson 4135 at 4:30.

• Apr 26: Rie Kubota Ando will be giving two practice talks:
  • Multi-document summarization by visualizing topical content, ANLP/NAACL Workshop on Automatic Summarization (joint work with Branimir Boguraev, Roy Byrd, and Mary Neff)
  • Mostly-unsupervised statistical segmentation of Japanese: Applications to kanji, NAACL (joint work with Lillian Lee)

• May 8: Dan Jurafsky, University of Colorado, Boulder:
  Probabilistic Models of Linguistic Knowledge: Evidence from Human Comprehension and Production
  Monday, May 8, 2000, 4:00 PM
  Morrill 106

  Abstract: Why should linguists care about probabilities? Wasn't the move to studying language at the purely symbolic level one of the great advances of the generative revolution of the 1950's and 60's? In this talk I suggest that while it is critical to continue to model deep, rich structural knowledge at many linguistic levels, it is equally critical to understand the way this knowledge is used probabilistically by human language users. I will summarize a number of results from our lab on the role of probability, and the directly related ideas of frequency, informativeness, and entropy, in human language processing. Our claim, drawing from our work and that of colleagues and predecessors dating back to Jespersen and even earlier, is that language processing is "probabilistic all the way down". Humans compute the probability of an interpretation in order to resolve lexical, syntactic, and thematic ambiguities. Humans compute the probability of words in language production to help determine the surface form the words should take. I will focus especially on our recent results on language production and the probabilistic representation of relations between words. This talk describes joint work with Alan Bell, Eric Fosler-Lussier, Daniel Gildea, Cynthia Girand, Michelle Gregory, Srini Narayanan, William D. Raymond, and Doug Roland.

  This talk is jointly sponsored by Cornell's department of Linguistics, Computer Science, and Cognitive Studies.

• May 9: Dan Jurafsky will lead a discussion on "Directions in computational linguistics", 4:00 PM, Morrill 106

CS775, Spring '00
Lillian Lee