An empirical study of building a strong baseline for constituency parsing

Jun Suzuki; Sho Takase; Hidetaka Kamigaito; Makoto Morishita; Masaaki Nagata

doi:10.18653/v1/p18-2097

An empirical study of building a strong baseline for constituency parsing

Jun Suzuki, Sho Takase, Hidetaka Kamigaito, Makoto Morishita, Masaaki Nagata

Center for Data-driven Science and Artificial Intelligence (CDS)

Nippon Telegraph & Telephone

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

14 Citations (Scopus)

Abstract

This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. We incorporate several techniques that were mainly developed in natural language generation tasks, e.g., machine translation and summarization, and demonstrate that the sequence-to-sequence model achieves the current top-notch parsers’ performance without requiring explicit task-specific knowledge or architecture of constituent parsing.

Original language	English
Title of host publication	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	612-618
Number of pages	7
ISBN (Electronic)	9781948087346
DOIs	https://doi.org/10.18653/v1/p18-2097
Publication status	Published - 2018
Event	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018 - Melbourne, Australia Duration: 2018 Jul 15 → 2018 Jul 20

Publication series

Name	ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	2

Conference

Conference	56th Annual Meeting of the Association for Computational Linguistics, ACL 2018
Country/Territory	Australia
City	Melbourne
Period	18/7/15 → 18/7/20

Access to Document

10.18653/v1/p18-2097

Cite this

Suzuki, J., Takase, S., Kamigaito, H., Morishita, M., & Nagata, M. (2018). An empirical study of building a strong baseline for constituency parsing. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) (pp. 612-618). (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p18-2097

Suzuki, Jun ; Takase, Sho ; Kamigaito, Hidetaka et al. / An empirical study of building a strong baseline for constituency parsing. ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2018. pp. 612-618 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{a6f43d6c5e744cf79b73c97be026393a,

title = "An empirical study of building a strong baseline for constituency parsing",

abstract = "This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. We incorporate several techniques that were mainly developed in natural language generation tasks, e.g., machine translation and summarization, and demonstrate that the sequence-to-sequence model achieves the current top-notch parsers{\textquoteright} performance without requiring explicit task-specific knowledge or architecture of constituent parsing.",

author = "Jun Suzuki and Sho Takase and Hidetaka Kamigaito and Makoto Morishita and Masaaki Nagata",

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",

doi = "10.18653/v1/p18-2097",

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 = "612--618",

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

address = "United States",

}

Suzuki, J, Takase, S, Kamigaito, H, Morishita, M & Nagata, M 2018, An empirical study of building a strong baseline for constituency parsing. in ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 2, Association for Computational Linguistics (ACL), pp. 612-618, 56th Annual Meeting of the Association for Computational Linguistics, ACL 2018, Melbourne, Australia, 18/7/15. https://doi.org/10.18653/v1/p18-2097

An empirical study of building a strong baseline for constituency parsing. / Suzuki, Jun; Takase, Sho; Kamigaito, Hidetaka et al.
ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2018. p. 612-618 (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers); Vol. 2).

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

TY - GEN

T1 - An empirical study of building a strong baseline for constituency parsing

AU - Suzuki, Jun

AU - Takase, Sho

AU - Kamigaito, Hidetaka

AU - Morishita, Makoto

AU - Nagata, Masaaki

PY - 2018

Y1 - 2018

N2 - This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. We incorporate several techniques that were mainly developed in natural language generation tasks, e.g., machine translation and summarization, and demonstrate that the sequence-to-sequence model achieves the current top-notch parsers’ performance without requiring explicit task-specific knowledge or architecture of constituent parsing.

AB - This paper investigates the construction of a strong baseline based on general purpose sequence-to-sequence models for constituency parsing. We incorporate several techniques that were mainly developed in natural language generation tasks, e.g., machine translation and summarization, and demonstrate that the sequence-to-sequence model achieves the current top-notch parsers’ performance without requiring explicit task-specific knowledge or architecture of constituent parsing.

UR - http://www.scopus.com/inward/record.url?scp=85063154153&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063154153&partnerID=8YFLogxK

U2 - 10.18653/v1/p18-2097

DO - 10.18653/v1/p18-2097

M3 - Conference contribution

AN - SCOPUS:85063154153

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

SP - 612

EP - 618

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

Suzuki J, Takase S, Kamigaito H, Morishita M, Nagata M. An empirical study of building a strong baseline for constituency parsing. In ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL). 2018. p. 612-618. (ACL 2018 - 56th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/p18-2097

An empirical study of building a strong baseline for constituency parsing

Abstract

Publication series

Conference

Access to Document

Other files and links

Fingerprint

Cite this