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

Granular Causality

Rutu Mulkar-MehtaInformation Sciences Institute at the University of Southern California[Home Page]

Notice:  Hosted by Vinay Chaudhri.

Date:  2011-07-15 at 14:00

Location:  AE201 (SRI A building)  (Directions)

   Abstract

It has long been the vision of AI researchers to build systems that are able to learn and understand causal patterns in discourse, as they read input text. It has been a special interest to people in the community to develop such systems so that new inferences can be made on the input discourse, and numerous causal patterns can be extracted from texts that may be from relatively different domains.

This is however a very hard problem as causality manifests itself differently in different domains and genres of discourse. Also, contrary to traditional perception of causality, causality is not always sequential in nature, it can be granular (where a fine grained event causes a coarse grained event) or sometimes oven continuous (where two events cause each other continuously and simultaneously). This talk is about granular causality, and identifying granular causality relations in discourse. Although this phenomenon is very common in discourse, there has been very limited work in this area, and no work done to extract such relations from discourse. In this talk, I describe my proposed theory of granular causality, and elaborate on how this theory can be applied to Natural language discourse to to help with the problems of information extraction and question answering, both being very important problems for learning by reading.

   Bio for Rutu Mulkar-Mehta

Rutu Mulkar-Mehta is a Ph.D. candidate in computer science at University of Southern California and works as a Research Assistant at Information Sciences Institute with Dr. Jerry Hobbs. She is interested in applying symbolic logic and statistics for solving problems related to Natural Language Understanding. Specifically, she works with Causality, Granularity, Learning by Reading, Question Answering, Information Extraction, Knowledge Representation and Reasoning. Before this, Rutu Mulkar-Mehta obtained her MS in Computer Science at USC, before which she got her Engineering degree in Computer Science in India.

Rutu Mulkar-Mehta has organized Learning by Reading Workshops at NAACL in 2010 and at IJCAI in 2011, and has been a summer intern at The Jeopardy Group at IBM Watson Research Center in 2010.

   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. 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 Builing E entrance signage.

SRI International
©2014 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy