Sentence modeling for extractive speech summarization

Berlin Chen, Hao Chin Chang, Kuan Yu Chen

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

9 Citations (Scopus)

Abstract

Extractive speech summarization, aiming to select an indicative set of sentences from a spoken document so as to concisely represent the most important aspects of the document, has emerged as an attractive area of research and experimentation. A recent school of thought is to employ the language modeling (LM) framework along with the Kullback-Leibler (KL) divergence measure for important sentence selection, which has shown preliminary promise for extractive speech summarization. Our work in this paper continues this general line of research in two significant aspects. First, we explore a novel sentence modeling approach built on top of the notion of relevance, where the relationship between a candidate summary sentence and the spoken document to be summarized is discovered through various granularities of context for relevance modeling. Second, not only lexical but also topical cues inherent in the spoken document are exploited for sentence modeling. Experiments on broadcast news summarization seem to demonstrate the performance merits of our methods when compared to several existing methods.

Original languageEnglish
Title of host publication2013 IEEE International Conference on Multimedia and Expo, ICME 2013
DOIs
Publication statusPublished - 2013 Oct 21
Event2013 IEEE International Conference on Multimedia and Expo, ICME 2013 - San Jose, CA, United States
Duration: 2013 Jul 152013 Jul 19

Publication series

NameProceedings - IEEE International Conference on Multimedia and Expo
ISSN (Print)1945-7871
ISSN (Electronic)1945-788X

Other

Other2013 IEEE International Conference on Multimedia and Expo, ICME 2013
CountryUnited States
CitySan Jose, CA
Period13/7/1513/7/19

Fingerprint

Experiments

Keywords

  • Kullback-Leibler divergence
  • Speech summarization
  • language modeling
  • sentence modeling

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Computer Science Applications

Cite this

Chen, B., Chang, H. C., & Chen, K. Y. (2013). Sentence modeling for extractive speech summarization. In 2013 IEEE International Conference on Multimedia and Expo, ICME 2013 [6607518] (Proceedings - IEEE International Conference on Multimedia and Expo). https://doi.org/10.1109/ICME.2013.6607518

Sentence modeling for extractive speech summarization. / Chen, Berlin; Chang, Hao Chin; Chen, Kuan Yu.

2013 IEEE International Conference on Multimedia and Expo, ICME 2013. 2013. 6607518 (Proceedings - IEEE International Conference on Multimedia and Expo).

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

Chen, B, Chang, HC & Chen, KY 2013, Sentence modeling for extractive speech summarization. in 2013 IEEE International Conference on Multimedia and Expo, ICME 2013., 6607518, Proceedings - IEEE International Conference on Multimedia and Expo, 2013 IEEE International Conference on Multimedia and Expo, ICME 2013, San Jose, CA, United States, 13/7/15. https://doi.org/10.1109/ICME.2013.6607518
Chen B, Chang HC, Chen KY. Sentence modeling for extractive speech summarization. In 2013 IEEE International Conference on Multimedia and Expo, ICME 2013. 2013. 6607518. (Proceedings - IEEE International Conference on Multimedia and Expo). https://doi.org/10.1109/ICME.2013.6607518
Chen, Berlin ; Chang, Hao Chin ; Chen, Kuan Yu. / Sentence modeling for extractive speech summarization. 2013 IEEE International Conference on Multimedia and Expo, ICME 2013. 2013. (Proceedings - IEEE International Conference on Multimedia and Expo).
@inproceedings{4bc847a59cfb4e29a795bc9ba9e7e93f,
title = "Sentence modeling for extractive speech summarization",
abstract = "Extractive speech summarization, aiming to select an indicative set of sentences from a spoken document so as to concisely represent the most important aspects of the document, has emerged as an attractive area of research and experimentation. A recent school of thought is to employ the language modeling (LM) framework along with the Kullback-Leibler (KL) divergence measure for important sentence selection, which has shown preliminary promise for extractive speech summarization. Our work in this paper continues this general line of research in two significant aspects. First, we explore a novel sentence modeling approach built on top of the notion of relevance, where the relationship between a candidate summary sentence and the spoken document to be summarized is discovered through various granularities of context for relevance modeling. Second, not only lexical but also topical cues inherent in the spoken document are exploited for sentence modeling. Experiments on broadcast news summarization seem to demonstrate the performance merits of our methods when compared to several existing methods.",
keywords = "Kullback-Leibler divergence, Speech summarization, language modeling, sentence modeling",
author = "Berlin Chen and Chang, {Hao Chin} and Chen, {Kuan Yu}",
year = "2013",
month = "10",
day = "21",
doi = "10.1109/ICME.2013.6607518",
language = "English",
isbn = "9781479900152",
series = "Proceedings - IEEE International Conference on Multimedia and Expo",
booktitle = "2013 IEEE International Conference on Multimedia and Expo, ICME 2013",

}

TY - GEN

T1 - Sentence modeling for extractive speech summarization

AU - Chen, Berlin

AU - Chang, Hao Chin

AU - Chen, Kuan Yu

PY - 2013/10/21

Y1 - 2013/10/21

N2 - Extractive speech summarization, aiming to select an indicative set of sentences from a spoken document so as to concisely represent the most important aspects of the document, has emerged as an attractive area of research and experimentation. A recent school of thought is to employ the language modeling (LM) framework along with the Kullback-Leibler (KL) divergence measure for important sentence selection, which has shown preliminary promise for extractive speech summarization. Our work in this paper continues this general line of research in two significant aspects. First, we explore a novel sentence modeling approach built on top of the notion of relevance, where the relationship between a candidate summary sentence and the spoken document to be summarized is discovered through various granularities of context for relevance modeling. Second, not only lexical but also topical cues inherent in the spoken document are exploited for sentence modeling. Experiments on broadcast news summarization seem to demonstrate the performance merits of our methods when compared to several existing methods.

AB - Extractive speech summarization, aiming to select an indicative set of sentences from a spoken document so as to concisely represent the most important aspects of the document, has emerged as an attractive area of research and experimentation. A recent school of thought is to employ the language modeling (LM) framework along with the Kullback-Leibler (KL) divergence measure for important sentence selection, which has shown preliminary promise for extractive speech summarization. Our work in this paper continues this general line of research in two significant aspects. First, we explore a novel sentence modeling approach built on top of the notion of relevance, where the relationship between a candidate summary sentence and the spoken document to be summarized is discovered through various granularities of context for relevance modeling. Second, not only lexical but also topical cues inherent in the spoken document are exploited for sentence modeling. Experiments on broadcast news summarization seem to demonstrate the performance merits of our methods when compared to several existing methods.

KW - Kullback-Leibler divergence

KW - Speech summarization

KW - language modeling

KW - sentence modeling

UR - http://www.scopus.com/inward/record.url?scp=84885651683&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84885651683&partnerID=8YFLogxK

U2 - 10.1109/ICME.2013.6607518

DO - 10.1109/ICME.2013.6607518

M3 - Conference contribution

AN - SCOPUS:84885651683

SN - 9781479900152

T3 - Proceedings - IEEE International Conference on Multimedia and Expo

BT - 2013 IEEE International Conference on Multimedia and Expo, ICME 2013

ER -