A comparative study of probabilistic ranking models for spoken document summarization

Shih Hsiang Lin, Yi Ting Chen, Hsin Min Wang, Berlin Chen

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

3 Citations (Scopus)

Abstract

The purpose of extractive document summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a target summarization ratio and then sequence them to form a concise summary. In the paper, we present a comparative study of various supervised and unsupervised probabilistic ranking models for spoken document summarization on the Chinese broadcast news. Moreover, we also investigate the possibility of using unsupervised summarizers to boost the performance of supervised summarizers when manual labels are not available for the training of supervised summarizers. Encouraging results were initially demonstrated.

Original languageEnglish
Title of host publication2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
Pages5025-5028
Number of pages4
DOIs
Publication statusPublished - 2008 Sep 16
Event2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP - Las Vegas, NV, United States
Duration: 2008 Mar 312008 Apr 4

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP
CountryUnited States
CityLas Vegas, NV
Period08/3/3108/4/4

Fingerprint

Labels
Statistical Models

Keywords

  • Extractive summarization
  • Probabilistic ranking models
  • Spoken document summarization
  • Unsupervised summarizers

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Lin, S. H., Chen, Y. T., Wang, H. M., & Chen, B. (2008). A comparative study of probabilistic ranking models for spoken document summarization. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP (pp. 5025-5028). [4518787] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4518787

A comparative study of probabilistic ranking models for spoken document summarization. / Lin, Shih Hsiang; Chen, Yi Ting; Wang, Hsin Min; Chen, Berlin.

2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 5025-5028 4518787 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).

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

Lin, SH, Chen, YT, Wang, HM & Chen, B 2008, A comparative study of probabilistic ranking models for spoken document summarization. in 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP., 4518787, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, pp. 5025-5028, 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP, Las Vegas, NV, United States, 08/3/31. https://doi.org/10.1109/ICASSP.2008.4518787
Lin SH, Chen YT, Wang HM, Chen B. A comparative study of probabilistic ranking models for spoken document summarization. In 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. p. 5025-5028. 4518787. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2008.4518787
Lin, Shih Hsiang ; Chen, Yi Ting ; Wang, Hsin Min ; Chen, Berlin. / A comparative study of probabilistic ranking models for spoken document summarization. 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP. 2008. pp. 5025-5028 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{6ccde1d658114beeb503d3d224bec3a0,
title = "A comparative study of probabilistic ranking models for spoken document summarization",
abstract = "The purpose of extractive document summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a target summarization ratio and then sequence them to form a concise summary. In the paper, we present a comparative study of various supervised and unsupervised probabilistic ranking models for spoken document summarization on the Chinese broadcast news. Moreover, we also investigate the possibility of using unsupervised summarizers to boost the performance of supervised summarizers when manual labels are not available for the training of supervised summarizers. Encouraging results were initially demonstrated.",
keywords = "Extractive summarization, Probabilistic ranking models, Spoken document summarization, Unsupervised summarizers",
author = "Lin, {Shih Hsiang} and Chen, {Yi Ting} and Wang, {Hsin Min} and Berlin Chen",
year = "2008",
month = "9",
day = "16",
doi = "10.1109/ICASSP.2008.4518787",
language = "English",
isbn = "1424414849",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
pages = "5025--5028",
booktitle = "2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP",

}

TY - GEN

T1 - A comparative study of probabilistic ranking models for spoken document summarization

AU - Lin, Shih Hsiang

AU - Chen, Yi Ting

AU - Wang, Hsin Min

AU - Chen, Berlin

PY - 2008/9/16

Y1 - 2008/9/16

N2 - The purpose of extractive document summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a target summarization ratio and then sequence them to form a concise summary. In the paper, we present a comparative study of various supervised and unsupervised probabilistic ranking models for spoken document summarization on the Chinese broadcast news. Moreover, we also investigate the possibility of using unsupervised summarizers to boost the performance of supervised summarizers when manual labels are not available for the training of supervised summarizers. Encouraging results were initially demonstrated.

AB - The purpose of extractive document summarization is to automatically select a number of indicative sentences, passages, or paragraphs from the original document according to a target summarization ratio and then sequence them to form a concise summary. In the paper, we present a comparative study of various supervised and unsupervised probabilistic ranking models for spoken document summarization on the Chinese broadcast news. Moreover, we also investigate the possibility of using unsupervised summarizers to boost the performance of supervised summarizers when manual labels are not available for the training of supervised summarizers. Encouraging results were initially demonstrated.

KW - Extractive summarization

KW - Probabilistic ranking models

KW - Spoken document summarization

KW - Unsupervised summarizers

UR - http://www.scopus.com/inward/record.url?scp=51449086490&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=51449086490&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2008.4518787

DO - 10.1109/ICASSP.2008.4518787

M3 - Conference contribution

AN - SCOPUS:51449086490

SN - 1424414849

SN - 9781424414840

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 5025

EP - 5028

BT - 2008 IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP

ER -