Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization

Guokan Shang; Wensi Ding; Zekun Zhang; Antoine J.P. Tixier; Polykarpos Meladianos; Michalis Vazirgiannis; Jean Pierre Lorré

doi:10.18653/v1/p18-1062

Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization

Guokan Shang
, Wensi Ding
, Zekun Zhang
, Antoine J.P. Tixier
, Polykarpos Meladianos
, Michalis Vazirgiannis
, Jean Pierre Lorré

Linagora
Athens Univ. of Econ. and Business

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

85 Citations (Scopus)

Abstract

We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations. Our work combines the strengths of multiple recent approaches while addressing their weaknesses. Moreover, we leverage recent advances in word embeddings and graph degeneracy applied to NLP to take exterior semantic knowledge into account, and to design custom diversity and informativeness measures. Experiments on the AMI and ICSI corpus show that our system improves on the state-of-the-art.

Original language	English
Title of host publication	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	664-674
Number of pages	11
ISBN (Electronic)	9781948087322
DOIs	https://doi.org/10.18653/v1/p18-1062
Publication status	Published - 1 Jan 2018
Event	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia Duration: 15 Jul 2018 → 20 Jul 2018

Publication series

Name	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	1

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/Territory	Australia
City	Melbourne
Period	15/07/18 → 20/07/18

Access to Document

10.18653/v1/p18-1062

Cite this

Shang, G., Ding, W., Zhang, Z., Tixier, A. J. P., Meladianos, P., Vazirgiannis, M., & Lorré, J. P. (2018). Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers) (pp. 664-674). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-1062

Shang, Guokan ; Ding, Wensi ; Zhang, Zekun et al. / Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. pp. 664-674 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{a4e27388c9f741a6873ff517d39e7afc,

title = "Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization",

abstract = "We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations. Our work combines the strengths of multiple recent approaches while addressing their weaknesses. Moreover, we leverage recent advances in word embeddings and graph degeneracy applied to NLP to take exterior semantic knowledge into account, and to design custom diversity and informativeness measures. Experiments on the AMI and ICSI corpus show that our system improves on the state-of-the-art.",

author = "Guokan Shang and Wensi Ding and Zekun Zhang and Tixier, \{Antoine J.P.\} and Polykarpos Meladianos and Michalis Vazirgiannis and Lorr{\'e}, \{Jean Pierre\}",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics; 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 ; Conference date: 15-07-2018 Through 20-07-2018",

year = "2018",

month = jan,

day = "1",

doi = "10.18653/v1/p18-1062",

language = "English",

series = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

publisher = "Association for Computational Linguistics (ACL)",

pages = "664--674",

booktitle = "ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

}

Shang, G, Ding, W, Zhang, Z, Tixier, AJP, Meladianos, P, Vazirgiannis, M & Lorré, JP 2018, Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. in ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 1, Association for Computational Linguistics (ACL), pp. 664-674, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 15/07/18. https://doi.org/10.18653/v1/p18-1062

Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. / Shang, Guokan; Ding, Wensi; Zhang, Zekun et al.
ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL), 2018. p. 664-674 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 1).

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

TY - GEN

T1 - Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization

AU - Shang, Guokan

AU - Ding, Wensi

AU - Zhang, Zekun

AU - Tixier, Antoine J.P.

AU - Meladianos, Polykarpos

AU - Vazirgiannis, Michalis

AU - Lorré, Jean Pierre

PY - 2018/1/1

Y1 - 2018/1/1

N2 - We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations. Our work combines the strengths of multiple recent approaches while addressing their weaknesses. Moreover, we leverage recent advances in word embeddings and graph degeneracy applied to NLP to take exterior semantic knowledge into account, and to design custom diversity and informativeness measures. Experiments on the AMI and ICSI corpus show that our system improves on the state-of-the-art.

AB - We introduce a novel graph-based framework for abstractive meeting speech summarization that is fully unsupervised and does not rely on any annotations. Our work combines the strengths of multiple recent approaches while addressing their weaknesses. Moreover, we leverage recent advances in word embeddings and graph degeneracy applied to NLP to take exterior semantic knowledge into account, and to design custom diversity and informativeness measures. Experiments on the AMI and ICSI corpus show that our system improves on the state-of-the-art.

U2 - 10.18653/v1/p18-1062

DO - 10.18653/v1/p18-1062

M3 - Conference contribution

AN - SCOPUS:85063086864

T3 - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 664

EP - 674

BT - ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

PB - Association for Computational Linguistics (ACL)

T2 - 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018

Y2 - 15 July 2018 through 20 July 2018

ER -

Shang G, Ding W, Zhang Z, Tixier AJP, Meladianos P, Vazirgiannis M et al. Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers). Association for Computational Linguistics (ACL). 2018. p. 664-674. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/p18-1062

Unsupervised abstractive meeting summarization with multi-sentence compression and budgeted submodular maximization

Abstract

Publication series

Conference

Access to Document

Fingerprint

Cite this