Sentence Reduction for Automatic Text Summarization

We present a novel sentence reduction system for automatically removing extraneous phrases from sentences that are extracted from a document for summarization purpose. The system uses multiple sources of knowledge to decide which phrases in an extracted sentence can be removed, including syntactic knowledge, context information, and statistics computed from a corpus which consists of examples written by human professionals. Reduction can significantly improve the conciseness of automatic summaries. 1 Motivation Current automatic summarizers usually rely on sentence extraction to produce summaries. Human professionals also often reuse the input documents to generate summaries; however, rather than simply extracting sentences and stringing them together, as most current summarizers do, humans often "edit" the extracted sentences in some way so that the resulting summary is concise and coherent. We analyzed a set of articles and identified six major operations that can be used ...

• Type: Conference
• Year: 2000
• Where: ANLP
• Authors: Hongyan Jing
• Keywords: ANLP 2000, Extracted Sentences, Extraneous Phrases, Sentence Reduction