An empirical study of span representations in argumentation structure parsing

Tatsuki Kuribayashi; Hiroki Ouchi; Naoya Inoue; Paul Reisert; Toshinori Miyoshi; Jun Suzuki; Kentaro Inui

An empirical study of span representations in argumentation structure parsing

Tatsuki Kuribayashi, Hiroki Ouchi, Naoya Inoue, Paul Reisert, Toshinori Miyoshi, Jun Suzuki, Kentaro Inui

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

23 Citations (Scopus)

Abstract

For several natural language processing (NLP) tasks, span representation is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (i) span representation originally developed for other NLP tasks and (ii) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.

Original language	English
Title of host publication	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	4691-4698
Number of pages	8
ISBN (Electronic)	9781950737482
Publication status	Published - 2020
Event	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy Duration: 2019 Jul 28 → 2019 Aug 2

Publication series

Name	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/Territory	Italy
City	Florence
Period	19/7/28 → 19/8/2

Cite this

Kuribayashi, T., Ouchi, H., Inoue, N., Reisert, P., Miyoshi, T., Suzuki, J., & Inui, K. (2020). An empirical study of span representations in argumentation structure parsing. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 4691-4698). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Kuribayashi, Tatsuki ; Ouchi, Hiroki ; Inoue, Naoya et al. / An empirical study of span representations in argumentation structure parsing. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 4691-4698 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{8b45ec9f27a24039a4c93f072daddc84,

title = "An empirical study of span representations in argumentation structure parsing",

abstract = "For several natural language processing (NLP) tasks, span representation is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (i) span representation originally developed for other NLP tasks and (ii) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.",

author = "Tatsuki Kuribayashi and Hiroki Ouchi and Naoya Inoue and Paul Reisert and Toshinori Miyoshi and Jun Suzuki and Kentaro Inui",

note = "Funding Information: This work was supported by JST CREST Grant Number JPMJCR1513, Japan. We would like to thank the laboratory members who gave us advice and all reviewers of this work for their useful comments and feedback. Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2020",

language = "English",

series = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

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

pages = "4691--4698",

booktitle = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "United States",

}

Kuribayashi, T, Ouchi, H, Inoue, N, Reisert, P, Miyoshi, T, Suzuki, J & Inui, K 2020, An empirical study of span representations in argumentation structure parsing. in ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 4691-4698, 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 19/7/28.

An empirical study of span representations in argumentation structure parsing. / Kuribayashi, Tatsuki; Ouchi, Hiroki; Inoue, Naoya et al.
ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 4691-4698 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

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

TY - GEN

T1 - An empirical study of span representations in argumentation structure parsing

AU - Kuribayashi, Tatsuki

AU - Ouchi, Hiroki

AU - Inoue, Naoya

AU - Reisert, Paul

AU - Miyoshi, Toshinori

AU - Suzuki, Jun

AU - Inui, Kentaro

N1 - Funding Information: This work was supported by JST CREST Grant Number JPMJCR1513, Japan. We would like to thank the laboratory members who gave us advice and all reviewers of this work for their useful comments and feedback. Publisher Copyright: © 2019 Association for Computational Linguistics

PY - 2020

Y1 - 2020

N2 - For several natural language processing (NLP) tasks, span representation is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (i) span representation originally developed for other NLP tasks and (ii) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.

AB - For several natural language processing (NLP) tasks, span representation is attracting considerable attention as a promising new technique; a common basis for an effective design has been established. With such basis, exploring task-dependent extensions for argumentation structure parsing (ASP) becomes an interesting research direction. This study investigates (i) span representation originally developed for other NLP tasks and (ii) a simple task-dependent extension for ASP. Our extensive experiments and analysis show that these representations yield high performance for ASP and provide some challenging types of instances to be parsed.

UR - http://www.scopus.com/inward/record.url?scp=85084068875&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084068875&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85084068875

T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 4691

EP - 4698

BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

Kuribayashi T, Ouchi H, Inoue N, Reisert P, Miyoshi T, Suzuki J et al. An empirical study of span representations in argumentation structure parsing. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 4691-4698. (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

An empirical study of span representations in argumentation structure parsing

Abstract

Publication series

Conference

Other files and links

Fingerprint

Cite this