Search |  Contact |  SRI Home Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap. Do not follow this link, or your host will be blocked from this site. This is a spider trap.A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A A ASRI International.  333 Ravenswood Avenue.  Menlo Park, CA 94025-3493. SRI International is a nonprofit corporation.

AIC Seminar Series

Generating Complex Discourse-level Questions with Knowledge of Discourse Relations

Rashmi Prasad[Home Page]

Notice:  Hosted by Vinay K. Chaudhri

Date:  Monday, November 8th 2010 at 4:00pm

Location:  EJ228 (SRI E building)  (Directions)


Automatic Question Generation (QG) from an input text or a knowledge base can be immensely useful for intelligent tutoring systems, and in general querying environments. In education systems, it can lead to more natural and effective student-tutor interactions. Challenges for this task are similar to classical NLG, namely, what to say (content selection), and how to say it (planning and realization). One approach currently being taken by some is to "overgenerate" questions from all content that "can" be questioned. Overgenerated questions may then be ranked or filtered based on informational criteria, domain-specific requirements, and meta-cognitive considerations. I will describe our work on automatically generating complex questions, such as causal, specificational and temporal questions, from input paragraphs. The fully automatic system results were submitted to the first shared task on question generation (QG-STEC) held in 2010. Our approach is centered around the accurate recognition of discourse relations, which provide the source for determining the questions types and the question content. For recognizing discourse relations, I will describe how the Penn Discourse Treebank (PDTB), a large-scale annotated corpus of lexicalized discourse relations that we have developed at UPenn, can be effectively exploited for discourse-level QG. Joint work with Nikhil Dinesh, Aravind Joshi, Prashanth Mannem, Eleni Miltsakaki, Bonnie Webber

   Bio for Rashmi Prasad

Dr. Rashmi Prasad is a Senior Research Scientist at the Institute for Research in Cognitive Science, University of Pennsylvania. Her research focuses on discourse and dialogue processing for natural language applications. Specific problems she has worked on include discourse parsing, anaphora resolution, dialogue act tagging, sentence planning in generation, question generation, and biomedical discourse-level information extraction. She has also done extensive work on developing linguistic resources for research, including the XTAG English grammar, the Penn Discourse Treebank, and the Biomedical Discourse Relation Bank. She has a PhD in Linguistics from the University of Pennsylvania and an M.A. in Linguistics from Jawaharlal University, New Delhi. Prior to joining Penn, she was a consultant at AT&T Labs, Research. She is currently also consulting for College of Health Sciences, University of Wisconsin-Milwaukee and Kaiser Permanente HealthConnect.

   Note for Visitors to SRI

Please arrive at least 10 minutes early as you will need to sign in by following instructions by the lobby phone at Building E (or call Wilma Lenz at 650 859 4904, or Eunice Tseng at 650 859 2799). SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the parking lots off Fourth Street. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. There are two entrances to SRI International located on Ravenswood Ave. Please check the Building E entrance signage.

SRI International
©2018 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy