Are extractive text summarisation techniques portable to broadcast news?

Heidi Christensen; Yoshihiko Gotoh; BalaKrishna Kolluru; Steve Renals

doi:10.1109/ASRU.2003.1318489

Are extractive text summarisation techniques portable to broadcast news?

Heidi Christensen, Yoshihiko Gotoh, BalaKrishna Kolluru, Steve Renals

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

Abstract / Description of output

In this paper we report on a series of experiments which compare the effect of individual features on both text and speech summarisation, the effect of basing the speech summaries on automatic speech recognition transcripts with varying word error rates, and the effect of summarisation approach and transcript source on summary quality. We show that classical text summarisation features (based on stylistic and content information) are portable to broadcast news. However, the quality of the speech transcripts as well as the difference in information structure between broadcast and newspaper news affect the usability of the individual features.

Original language	English
Title of host publication	Automatic Speech Recognition and Understanding, 2003 IEEE Workshop on
Subtitle of host publication	ASRU '03.
Publisher	Institute of Electrical and Electronics Engineers
Pages	489-494
ISBN (Print)	0-7803-7980-2
DOIs	https://doi.org/10.1109/ASRU.2003.1318489
Publication status	Published - 2003
Event	2003 IEEE Workshop on Automatic Speech Recognition and Understanding - St. Thomas, Virgin Islands, U.S. Duration: 30 Nov 2003 → 4 Dec 2003

Workshop

Workshop	2003 IEEE Workshop on Automatic Speech Recognition and Understanding
Country/Territory	Virgin Islands, U.S.
City	St. Thomas
Period	30/11/03 → 4/12/03

Access to Document

10.1109/ASRU.2003.1318489

asru03-portableSubmitted manuscript, 117 KB

http://ieeexplore.ieee.org/lpdocs/epic03/wrapper.htm?arnumber=1318489

Cite this

@inproceedings{e00b0b9c435e4fa9816f3c1ad959fe59,

title = "Are extractive text summarisation techniques portable to broadcast news?",

abstract = "In this paper we report on a series of experiments which compare the effect of individual features on both text and speech summarisation, the effect of basing the speech summaries on automatic speech recognition transcripts with varying word error rates, and the effect of summarisation approach and transcript source on summary quality. We show that classical text summarisation features (based on stylistic and content information) are portable to broadcast news. However, the quality of the speech transcripts as well as the difference in information structure between broadcast and newspaper news affect the usability of the individual features.",

author = "Heidi Christensen and Yoshihiko Gotoh and BalaKrishna Kolluru and Steve Renals",

year = "2003",

doi = "10.1109/ASRU.2003.1318489",

language = "English",

isbn = "0-7803-7980-2",

pages = "489--494",

booktitle = "Automatic Speech Recognition and Understanding, 2003 IEEE Workshop on",

publisher = "Institute of Electrical and Electronics Engineers",

note = "2003 IEEE Workshop on Automatic Speech Recognition and Understanding ; Conference date: 30-11-2003 Through 04-12-2003",

}

Christensen, H, Gotoh, Y, Kolluru, B & Renals, S 2003, Are extractive text summarisation techniques portable to broadcast news? in Automatic Speech Recognition and Understanding, 2003 IEEE Workshop on: ASRU '03.. Institute of Electrical and Electronics Engineers, pp. 489-494, 2003 IEEE Workshop on Automatic Speech Recognition and Understanding, St. Thomas, Virgin Islands, U.S., 30/11/03. https://doi.org/10.1109/ASRU.2003.1318489

Are extractive text summarisation techniques portable to broadcast news? / Christensen, Heidi; Gotoh, Yoshihiko; Kolluru, BalaKrishna et al.
Automatic Speech Recognition and Understanding, 2003 IEEE Workshop on: ASRU '03.. Institute of Electrical and Electronics Engineers, 2003. p. 489-494.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution