Robust Temporal Processing of News

Robust Temporal Processing of News Inderjeet Mani and George Wilson The MITRE Corporation, W640 11493 Sunset Hills Road Reston, Virginia 22090 {imani, gwilson}@mitre.org Abstract We introduce an annotation scheme for temporal expressions, and describe a method for resolving temporal expressions in print and broadcast news. The system, which is based on both hand-crafted and machine-learnt rules, achieves an 83.2% accuracy (F- measure) against hand-annotated data. Some initial steps towards tagging event chronologies are also described. Introduction The extraction of temporal information from news offers many interesting linguistic challenges in the coverage and representation of temporal expressions. It is also of considerable practical importance in a variety of current applications. For example, in question-answering, it is useful to be able to resolve the underlined reference in “the next year, he won the Open” in response to a question like “When did X win the U.S. Open?”. In multi- document summarization, providing fine- grained chronologies of events over time (e.g., for a biography of a person, or a history of a crisis) can be very useful. In information retrieval, being able to index broadcast news stories by event times allows for powerful multimedia browsing capabilities. Our focus here, in contrast to previous work such as (MUC 1998), is on resolving time expressions, especially indexical expressions like “now”, “today”, “tomorrow”, “next Tuesday”, “two weeks ago”, “20 mins after the next hour”, etc., which designate times that are dependent on the speaker and some a “reference” time1. In this paper, we discuss temporal annotation scheme for representing dates and times in temporal expressions. This is followed by details and performance measures for a tagger to extract this information from news sources. The tagger uses a variety of hand-crafted and machine-discovered rules, all of which rely on lexical features that are easily recognized. We also report on a preliminary effort towards constructing event chronologies from this data. 1 Annotation Scheme Any annotation scheme should aim to be simple enough to be executed by humans, and yet precise enough for use in various natural language processing tasks. Our approach (Wilson et al. 2000) has been to annotate those things that a human could be expected to tag. Our representation of times uses the ISO standard CC:YY:MM:DD:HH:XX:SS, with an optional time zone (ISO-8601 1997). In other words, time points are represented in terms of a calendric coordinate system, rather than a real number line. The standard also supports the representation of weeks and days of the week in the format CC:YY:Wwwd where ww specifies which week within the year (1-53) and d specifies the day of the week (1-7). For example, “last week” might receive the VAL 20:00:W16. A time (TIMEX) expression (of type TIME or DATE) representing a particular point on the ISO line, e.g., “Tuesday, November 2, 2000” (or “next Tuesday”) is represented with the ISO time Value (VAL), 20:00:11:02. Interval expressions like “From 1 Some of these indexicals have been called “relative times” in the (MUC 1998) temporal tagging task. May 1999 to June …

Content truncated to 500 words