Unsupervised Discovery of Narratives from Text
| Nate Chambers | Stanford University |
Notice: hosted by Eric Yeh
Date: Thursday May 22, 2008 at 16:00
Location: EJ228 (SRI E building) (Directions)
|
|
Hand-coded scripts were used in the 1970-80s as knowledge backbones that enabled inference and other NLP tasks requiring deep semantic knowledge. I'll describe a proposed unsupervised induction of similar schemata called Narrative Event Chains from raw newswire text. A narrative chain is a partially ordered set of events related by a common protagonist. I'll describe a three step process to learning narrative chains. The first uses unsupervised distributional methods to learn narrative relations between events sharing coreferring entity arguments. The second applies a temporal classifier to partially order the connected events. Finally, the third prunes and clusters self-contained chains from the space of events. Two evaluations are introduced: the narrative cloze to evaluate event relatedness, and an order coherence task to evaluate narrative order. |
|
|
Please arrive at least 10 minutes early in order to sign in and be escorted to the conference room. SRI is located at 333 Ravenswood Avenue in Menlo Park. Visitors may park in the visitors lot in front of Building E, and should follow the instructions by the lobby phone to be escorted to the meeting room. Detailed directions to SRI, as well as maps, are available from the Visiting AIC web page. ![]()
©2013 SRI International 333 Ravenswood Avenue, Menlo Park, CA 94025-3493
SRI International is an independent, nonprofit corporation. Privacy policy |