From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)?

Reut Tsarfaty; Dan Bareket; Stav Klein; Amit Seker

From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)?

Reut Tsarfaty
, Dan Bareket
, Stav Klein
, Amit Seker

Bar-Ilan University

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

23 Scopus citations

Abstract

It has been exactly a decade since the first establishment of SPMRL, a research initiative unifying multiple research efforts to address the peculiar challenges of Statistical Parsing for Morphologically-Rich Languages (MRLs). Here we reflect on parsing MRLs in that decade, highlight the solutions and lessons learned for the architectural, modeling and lexical challenges in the pre-neural era, and argue that similar challenges re-emerge in neural architectures for MRLs. We then aim to offer a climax, suggesting that incorporating symbolic ideas proposed in SPMRL terms into nowadays neural architectures has the potential to push NLP for MRLs to a new level. We sketch a strategies for designing Neural Models for MRLs (NMRL), and showcase preliminary support for these strategies via investigating the task of multi-tagging in Hebrew, a morphologically-rich, high-fusion, language.

Original language	English
Title of host publication	ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	7396-7408
Number of pages	13
ISBN (Electronic)	9781952148255
State	Published - 2020
Event	58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 - Virtual, Online, United States Duration: 5 Jul 2020 → 10 Jul 2020

Publication series

Name	Proceedings of the Annual Meeting of the Association for Computational Linguistics
ISSN (Print)	0736-587X

Conference

Conference	58th Annual Meeting of the Association for Computational Linguistics, ACL 2020
Country/Territory	United States
City	Virtual, Online
Period	5/07/20 → 10/07/20

Bibliographical note

Publisher Copyright:
© 2020 Association for Computational Linguistics

Funding

We thank Clara Vania, Adam Lopez, and members of the Edinburgh-NLP seminar, Yoav Goldberg, Ido Dagan, and members of the BIU-NLP seminar, for intriguing discussions on earlier presentations of this work. This research is kindly supported by the Israel Science Foundation (ISF), grant No. 1739/16, and by the European Research Council (ERC), under the Europoean Union Horizon 2020 research and innovation programme, grant No. 677352.

Funders	Funder number
Clara Vania
Europoean Union Horizon 2020 research and innovation programme
Horizon 2020 Framework Programme	677352
European Commission
Israel Science Foundation	1739/16

Cite this

Tsarfaty, R., Bareket, D., Klein, S., & Seker, A. (2020). From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)? In ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 7396-7408). (Proceedings of the Annual Meeting of the Association for Computational Linguistics). Association for Computational Linguistics (ACL).

Tsarfaty, Reut ; Bareket, Dan ; Klein, Stav et al. / From SPMRL to NMRL : What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)?. ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. pp. 7396-7408 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

@inproceedings{5989e54fcba044ff83e6f8acecf90f6b,

title = "From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)?",

abstract = "It has been exactly a decade since the first establishment of SPMRL, a research initiative unifying multiple research efforts to address the peculiar challenges of Statistical Parsing for Morphologically-Rich Languages (MRLs). Here we reflect on parsing MRLs in that decade, highlight the solutions and lessons learned for the architectural, modeling and lexical challenges in the pre-neural era, and argue that similar challenges re-emerge in neural architectures for MRLs. We then aim to offer a climax, suggesting that incorporating symbolic ideas proposed in SPMRL terms into nowadays neural architectures has the potential to push NLP for MRLs to a new level. We sketch a strategies for designing Neural Models for MRLs (NMRL), and showcase preliminary support for these strategies via investigating the task of multi-tagging in Hebrew, a morphologically-rich, high-fusion, language.",

author = "Reut Tsarfaty and Dan Bareket and Stav Klein and Amit Seker",

note = "Publisher Copyright: {\textcopyright} 2020 Association for Computational Linguistics; 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020 ; Conference date: 05-07-2020 Through 10-07-2020",

year = "2020",

language = "אנגלית",

series = "Proceedings of the Annual Meeting of the Association for Computational Linguistics",

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

pages = "7396--7408",

booktitle = "ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

address = "ארצות הברית",

}

Tsarfaty, R, Bareket, D, Klein, S & Seker, A 2020, From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)? in ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Proceedings of the Annual Meeting of the Association for Computational Linguistics, Association for Computational Linguistics (ACL), pp. 7396-7408, 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020, Virtual, Online, United States, 5/07/20.

From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)? / Tsarfaty, Reut; Bareket, Dan; Klein, Stav et al.
ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2020. p. 7396-7408 (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

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

TY - GEN

T1 - From SPMRL to NMRL

T2 - 58th Annual Meeting of the Association for Computational Linguistics, ACL 2020

AU - Tsarfaty, Reut

AU - Bareket, Dan

AU - Klein, Stav

AU - Seker, Amit

PY - 2020

Y1 - 2020

N2 - It has been exactly a decade since the first establishment of SPMRL, a research initiative unifying multiple research efforts to address the peculiar challenges of Statistical Parsing for Morphologically-Rich Languages (MRLs). Here we reflect on parsing MRLs in that decade, highlight the solutions and lessons learned for the architectural, modeling and lexical challenges in the pre-neural era, and argue that similar challenges re-emerge in neural architectures for MRLs. We then aim to offer a climax, suggesting that incorporating symbolic ideas proposed in SPMRL terms into nowadays neural architectures has the potential to push NLP for MRLs to a new level. We sketch a strategies for designing Neural Models for MRLs (NMRL), and showcase preliminary support for these strategies via investigating the task of multi-tagging in Hebrew, a morphologically-rich, high-fusion, language.

AB - It has been exactly a decade since the first establishment of SPMRL, a research initiative unifying multiple research efforts to address the peculiar challenges of Statistical Parsing for Morphologically-Rich Languages (MRLs). Here we reflect on parsing MRLs in that decade, highlight the solutions and lessons learned for the architectural, modeling and lexical challenges in the pre-neural era, and argue that similar challenges re-emerge in neural architectures for MRLs. We then aim to offer a climax, suggesting that incorporating symbolic ideas proposed in SPMRL terms into nowadays neural architectures has the potential to push NLP for MRLs to a new level. We sketch a strategies for designing Neural Models for MRLs (NMRL), and showcase preliminary support for these strategies via investigating the task of multi-tagging in Hebrew, a morphologically-rich, high-fusion, language.

UR - https://www.scopus.com/pages/publications/85098434249

M3 - ???researchoutput.researchoutputtypes.contributiontobookanthology.conference???

AN - SCOPUS:85098434249

T3 - Proceedings of the Annual Meeting of the Association for Computational Linguistics

SP - 7396

EP - 7408

BT - ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

Y2 - 5 July 2020 through 10 July 2020

ER -

Tsarfaty R, Bareket D, Klein S, Seker A. From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)? In ACL 2020 - 58th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 7396-7408. (Proceedings of the Annual Meeting of the Association for Computational Linguistics).

From SPMRL to NMRL: What did we learn (and Unlearn) in a decade of parsing Morphologically-Rich Languages (MRLs)?

Abstract

Publication series

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this