TERQAS: Temporal Event Recognition for Question Answering Systems

Leader: Prof. James Pustejovsky

Participants: Luc Belanger, Jose Castano, David Day, Lisa Ferro, Robert Gaizauskas, Patrick Hanks, Bob Ingria, Graham Katz, Marcia Lazo, Dragomir Radev, Anna Rumshishky, Antonio Sanfilippo, Roser Sauri, Andrea Setzer, Ed Slavich, Beth Sundheim, Marc Verhagen

Products:
Browse or download a summary briefing developed at the conclusion of the workshop.

View a final report on the work carried out in this workshop.

Overveiw:
From January 30, 2002, through July 22, 2002, a workshop, funded through the National Regional Research Center (NRRC), was held at MITRE Bedford and Brandeis University. The funding was fully sponsored by the Advanced Research Development Agency (ARDA). This document reports their activities and accomplishments.

The purpose of this workshop was to address the problem of how to answer temporally-based questions about the events and entities in text, specifically news articles. For example, currently questions such as those shown below are not supported by question answering systems.

What characterizes these questions as beyond the scope of current systems is the following: they refer, respectively, to the temporal aspects of the properties of the entities being questioned, the relative ordering of events in the world, and events that are mentioned in news articles, but which have never occurred. There has recently been a renewed interest in temporal and event-based reasoning in language and text, particularly as applied to information extraction and reasoning tasks (cf. Mani and Wilson, 2000, ACL Workshop on Spatial and Temporal Reasoning, 2001, Annotation Standards for Temporal Information in Natural Language, LREC 2002). Several papers from the workshop point to promising directions for time representation and identification (cf. Filatova and Hovy, 2001, Schilder and Habel, 2001, Setzer, 2002). Many issues relating to temporal and event identification have remained unresolved, however, and it was these issues that the workshop addressed. Specifically, the workshop goals were twofold: (a) to examine how to formally distinguish events and their temporal anchoring in language (text); and (b) to develop algorithms for ordering events in text relative to each other, and the operations for computing closure over an entire discourse of events.

Four basic problems in event-temporal identification were addressed in the workshop:

If you are interested in obtaining any of the data generated in the course of this workshop, please contact David Day, day@mitre.org.