TARSQI

Temporal Awareness and Reasoning Systems
for Question Interpretation

Prime Contractor Brandeis University (PI: James Pustejovsky)
Sub-Contractor 1 GeorgeTown University (PI: Inderjeet Mani)
Sub-Contractor 2 ISI (PI: Jerry Hobbs)

Motivation and Aims

This research builds on two previous ARDA-funded workshops, both devoted to temporal and event recognition for question answering systems (TERQAS, 2002, TANGO, 2003). These workshops created the infrastructure for temporal reasoning, by establishing a rich specification language called TimeML for representing events, temporal expressions, and the relations between them, and creating a gold standard called TIMEBANK1.1, for testing algorithms such as those being proposed in this application.

The TARSQI Project will allow AQUAINT developers and analysts to sort and organize information in NL texts based on their temporal characteristics. Specifically, we will develop algorithms that tag mentions of events in NL texts, tag time expressions and normalize them, and temporally anchor and order the events. We will also develop temporal reasoning algorithms that operate on the resulting event-time graphs for each document. These temporal reasoning algorithms will include a graph query capability, that will, for example, find when a particular event occurs, or which events occur in a time period. They will also include a temporal closure algorithm that will allow more complete coverage of queries (by using the transitivity of temporal precedence and inclusion relationships to insert additional links into the graph), and a timelining algorithm that provides chronological views at various granularities of an event graph as a whole or a region of it. We will also develop a capability to compare event graphs across documents. Finally, we will develop a model of the typical durations of various kinds of events.

Objectives

• Develop technology for annotating temporal information in natural language text, extracting temporal information from text, and reasoning about temporal information

• Make technology available for use in improved question-answering in AQUAINT, as well as for embedding in analyst toolkits

• Integrate tools with AQUAINT testbed