Generating Natural Language Summaries from Multiple On-Line Sources
Year: 1997
Type: article
Abstract: We present a methodology for summarization of news on current events. Our approach is included in a system, called SUMMONS which presents news summaries to the user in a natural language form along with appropriate background (historical)information from both textual (newswire) and structured (database)knowledge sources. The system presents novel approaches to several problems: summarization of multiple sources, summarization of multiple articles, symbolic summarization through text understanding and generation, asynchronous summarization and generation of textual updates. We pay specific attention to the generation of summaries that include descriptions of entities such as people and places. We show how certain classes of lexical resources can be automatically extracted from on-line corpora and used in the generation of textual summaries. We describe our approach to solving the interoperability problem of the various components by wrapping all system modules with facilitators which effect the communication between the components using a standardized language. We present a plan for completion of the research as well as a set of metrics that can be used in measuring the performance of the system.
DOI: 10.7916/d83n2b7j
Author: Radev, Dragomir R.
Institution: Columbia University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W1497212108