Creator of Knowledge
Information Resources Management Association
Advancing the Concepts & Practices of Information Resources Management in Modern Organizations

Time-Indexer: A Tool for Extracting Temporal References from Business News

Time-Indexer: A Tool for Extracting Temporal References from Business News
View Free PDF
Author(s): Pawel Jan Kalczynski (University of Toledo, USA), Witold Abramowicz (The Poznan University of Economics, Poland), Krzysztof Wecel (The Poznan University of Economics, Poland) and Tomasz Kazmarek (The Poznan University of Economics, Poland)
Copyright: 2003
Pages: 4
Source title: Information Technology & Organizations: Trends, Issues, Challenges & Solutions
Source Editor(s): Mehdi Khosrow-Pour, D.B.A. (Information Resources Management Association, USA)
DOI: 10.4018/978-1-59140-066-0.ch223
ISBN13: 9781616921248
EISBN13: 9781466665330


The idea behind time-indexing is that documents, apart from for their semantic context, have a temporal context. The context places events described in documents on the time axis. One way of defining temporal contexts is to extract temporal references from documents. The article presents a tool for extracting time (temporal) references from news documents. It employs a set of simple rules and a finite state automaton to compute time indices of documents based on temporal references and publication dates. As distinct from other solutions this tool is based on pattern matching rather than on lexical-syntactical analysis. The paper describes the time indexer and the results of experiments conducted with the tool. The experiment consisted of computing time indices for a collection of business news documents. Preliminary results show that the time indexer produces satisfactory results in terms of its simplicity.

Body Bottom