Edinburgh Research Explorer

Exploring the style-technique interaction in extractive summarization of broadcast news

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication2003 IEEE Workshop on Automatic Speech Recognition and Understanding, Proceedings of the
Subtitle of host publicationASRU '03
PublisherInstitute of Electrical and Electronics Engineers (IEEE)
Pages495-500
ISBN (Print)0-7803-7980-2
DOIs
Publication statusPublished - 2003
Event2003 IEEE Workshop on Automatic Speech Recognition and Understanding - St. Thomas, Virgin Islands, U.S.
Duration: 30 Nov 20034 Dec 2003

Workshop

Workshop2003 IEEE Workshop on Automatic Speech Recognition and Understanding
CountryVirgin Islands, U.S.
CitySt. Thomas
Period30/11/034/12/03

Abstract

In this paper we seek to explore the interaction between the style of a broadcast news story and its summarization technique. We report the performance of three different summarization techniques on broadcast news stories, which are split into planned speech and spontaneous speech. The initial results indicate that some summarization techniques work better for the documents with spontaneous speech than for those with planned speech. Even for human beings some documents are inherently difficult to summarize. We observe this correlation between degree of difficulty in summarizing and performance of the three automatic summarizers. Given the high frequency of named entities in broadcast news and even greater number of references to these named entities, we also gauge the effect of named entity and co-reference resolution in a news story, on the performance of these summarizers.

Event

2003 IEEE Workshop on Automatic Speech Recognition and Understanding

30/11/034/12/03

St. Thomas, Virgin Islands, U.S.

Event: Workshop

Download statistics

No data available

ID: 27412118