Term-Weighting for Summarization of Multi-party Spoken Dialogues

Gabriel Murray; Steve Renals

doi:10.1007/978-3-540-78155-4_14

Term-Weighting for Summarization of Multi-party Spoken Dialogues

Gabriel Murray, Steve Renals

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

Abstract

This paper explores the issue of term-weighting in the genre of spontaneous, multi-party spoken dialogues, with the intent of using such term-weights in the creation of extractive meeting summaries. The field of text information retrieval has yielded many term-weighting techniques to import for our purposes; this paper implements and compares several of these, namely tf.idf, Residual IDF and Gain. We propose that term-weighting for multi-party dialogues can exploit patterns in word usage among participant speakers, and introduce the su.idf metric as one attempt to do so. Results for all metrics are reported on both manual and automatic speech recognition (ASR) transcripts, and on both the ICSI and AMI meeting corpora.

Original language	English
Title of host publication	Machine Learning for Multimodal Interaction
Subtitle of host publication	4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers
Editors	Andrei Popescu-Belis, Steve Renals, Hervé Bourlard
Place of Publication	Berlin, Heidelberg
Publisher	Springer
Pages	156-167
Number of pages	12
ISBN (Electronic)	978-3-540-78155-4
ISBN (Print)	978-3-540-78154-7
DOIs	https://doi.org/10.1007/978-3-540-78155-4_14
Publication status	Published - 2008
Event	4th International Workshop MLMI 2007 - Brno, Czech Republic Duration: 28 Jun 2007 → 30 Jun 2007

Publication series

Name	Lecture Notes in Computer Science
Publisher	Springer Berlin Heidelberg
Volume	4892
ISSN (Print)	0302-9743

Workshop

Workshop	4th International Workshop MLMI 2007
Country/Territory	Czech Republic
City	Brno
Period	28/06/07 → 30/06/07

Access to Document

10.1007/978-3-540-78155-4_14

48920155Submitted manuscript, 153 KB

http://dx.doi.org/10.1007/978-3-540-78155-4_14

Cite this

Murray, G., & Renals, S. (2008). Term-Weighting for Summarization of Multi-party Spoken Dialogues. In A. Popescu-Belis, S. Renals, & H. Bourlard (Eds.), Machine Learning for Multimodal Interaction: 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers (pp. 156-167). (Lecture Notes in Computer Science; Vol. 4892). Springer. https://doi.org/10.1007/978-3-540-78155-4_14

Murray, Gabriel ; Renals, Steve. / Term-Weighting for Summarization of Multi-party Spoken Dialogues. Machine Learning for Multimodal Interaction: 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers. editor / Andrei Popescu-Belis ; Steve Renals ; Hervé Bourlard. Berlin, Heidelberg : Springer, 2008. pp. 156-167 (Lecture Notes in Computer Science).

@inbook{a8e15283721447b48d3983c3c81ef340,

title = "Term-Weighting for Summarization of Multi-party Spoken Dialogues",

abstract = "This paper explores the issue of term-weighting in the genre of spontaneous, multi-party spoken dialogues, with the intent of using such term-weights in the creation of extractive meeting summaries. The field of text information retrieval has yielded many term-weighting techniques to import for our purposes; this paper implements and compares several of these, namely tf.idf, Residual IDF and Gain. We propose that term-weighting for multi-party dialogues can exploit patterns in word usage among participant speakers, and introduce the su.idf metric as one attempt to do so. Results for all metrics are reported on both manual and automatic speech recognition (ASR) transcripts, and on both the ICSI and AMI meeting corpora.",

author = "Gabriel Murray and Steve Renals",

year = "2008",

doi = "10.1007/978-3-540-78155-4\_14",

language = "English",

isbn = "978-3-540-78154-7",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "156--167",

editor = "Andrei Popescu-Belis and Steve Renals and Herv{\'e} Bourlard",

booktitle = "Machine Learning for Multimodal Interaction",

address = "United Kingdom",

note = "4th International Workshop MLMI 2007 ; Conference date: 28-06-2007 Through 30-06-2007",

}

Murray, G & Renals, S 2008, Term-Weighting for Summarization of Multi-party Spoken Dialogues. in A Popescu-Belis, S Renals & H Bourlard (eds), Machine Learning for Multimodal Interaction: 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers. Lecture Notes in Computer Science, vol. 4892, Springer, Berlin, Heidelberg, pp. 156-167, 4th International Workshop MLMI 2007, Brno, Czech Republic, 28/06/07. https://doi.org/10.1007/978-3-540-78155-4_14

Term-Weighting for Summarization of Multi-party Spoken Dialogues. / Murray, Gabriel; Renals, Steve.
Machine Learning for Multimodal Interaction: 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers. ed. / Andrei Popescu-Belis; Steve Renals; Hervé Bourlard. Berlin, Heidelberg: Springer, 2008. p. 156-167 (Lecture Notes in Computer Science; Vol. 4892).

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

TY - CHAP

T1 - Term-Weighting for Summarization of Multi-party Spoken Dialogues

AU - Murray, Gabriel

AU - Renals, Steve

PY - 2008

Y1 - 2008

N2 - This paper explores the issue of term-weighting in the genre of spontaneous, multi-party spoken dialogues, with the intent of using such term-weights in the creation of extractive meeting summaries. The field of text information retrieval has yielded many term-weighting techniques to import for our purposes; this paper implements and compares several of these, namely tf.idf, Residual IDF and Gain. We propose that term-weighting for multi-party dialogues can exploit patterns in word usage among participant speakers, and introduce the su.idf metric as one attempt to do so. Results for all metrics are reported on both manual and automatic speech recognition (ASR) transcripts, and on both the ICSI and AMI meeting corpora.

AB - This paper explores the issue of term-weighting in the genre of spontaneous, multi-party spoken dialogues, with the intent of using such term-weights in the creation of extractive meeting summaries. The field of text information retrieval has yielded many term-weighting techniques to import for our purposes; this paper implements and compares several of these, namely tf.idf, Residual IDF and Gain. We propose that term-weighting for multi-party dialogues can exploit patterns in word usage among participant speakers, and introduce the su.idf metric as one attempt to do so. Results for all metrics are reported on both manual and automatic speech recognition (ASR) transcripts, and on both the ICSI and AMI meeting corpora.

U2 - 10.1007/978-3-540-78155-4_14

DO - 10.1007/978-3-540-78155-4_14

M3 - Chapter

SN - 978-3-540-78154-7

T3 - Lecture Notes in Computer Science

SP - 156

EP - 167

BT - Machine Learning for Multimodal Interaction

A2 - Popescu-Belis, Andrei

A2 - Renals, Steve

A2 - Bourlard, Hervé

PB - Springer

CY - Berlin, Heidelberg

T2 - 4th International Workshop MLMI 2007

Y2 - 28 June 2007 through 30 June 2007

ER -

Murray G, Renals S. Term-Weighting for Summarization of Multi-party Spoken Dialogues. In Popescu-Belis A, Renals S, Bourlard H, editors, Machine Learning for Multimodal Interaction: 4th International Workshop, MLMI 2007, Brno, Czech Republic, June 28-30, 2007, Revised Selected Papers. Berlin, Heidelberg: Springer. 2008. p. 156-167. (Lecture Notes in Computer Science). doi: 10.1007/978-3-540-78155-4_14

Term-Weighting for Summarization of Multi-party Spoken Dialogues

Abstract

Publication series

Workshop

Access to Document

Fingerprint

Cite this