QANom: Question-Answer driven SRL for Nominalizations

Ayal Klein; Jonathan Mamou; Valentina Pyatkin; Daniela Brook Weiss; Hangfeng He; Dan Roth; Luke Zettlemoyer; Ido Dagan

QANom: Question-Answer driven SRL for Nominalizations

Ayal Klein, Jonathan Mamou, Valentina Pyatkin, Daniela Brook Weiss, Hangfeng He, Dan Roth, Luke Zettlemoyer, Ido Dagan

Department of Computer Science

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

23 Scopus citations

Abstract

We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.

Original language	English
Title of host publication	COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference
Editors	Donia Scott, Nuria Bel, Chengqing Zong
Publisher	Association for Computational Linguistics (ACL)
Pages	3069-3083
Number of pages	15
ISBN (Electronic)	9781952148279
State	Published - 2020
Event	28th International Conference on Computational Linguistics, COLING 2020 - Virtual, Online, Spain Duration: 8 Dec 2020 → 13 Dec 2020

Publication series

Name	COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

Conference

Conference	28th International Conference on Computational Linguistics, COLING 2020
Country/Territory	Spain
City	Virtual, Online
Period	8/12/20 → 13/12/20

Bibliographical note

Publisher Copyright:
© 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

Funding

This work was supported in part by grants from Intel Labs, Facebook, the Israel Science Foundation grant 1951/17 and the German Research Foundation through the German-Israeli Project Cooperation (DIP, grant DA 1600/1-1).

Funders	Funder number
DIP	DA 1600/1-1
German-Israeli Project Cooperation
Intel Labs
Deutsche Forschungsgemeinschaft
Israel Science Foundation	1951/17

Cite this

Klein, A., Mamou, J., Pyatkin, V., Weiss, D. B., He, H., Roth, D., Zettlemoyer, L., & Dagan, I. (2020). QANom: Question-Answer driven SRL for Nominalizations. In D. Scott, N. Bel, & C. Zong (Eds.), COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference (pp. 3069-3083). (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

Klein, Ayal ; Mamou, Jonathan ; Pyatkin, Valentina et al. / QANom : Question-Answer driven SRL for Nominalizations. COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. editor / Donia Scott ; Nuria Bel ; Chengqing Zong. Association for Computational Linguistics (ACL), 2020. pp. 3069-3083 (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference).

@inproceedings{5165cc303f4e4dc7a26c5b992781fe1d,

title = "QANom: Question-Answer driven SRL for Nominalizations",

abstract = "We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.",

author = "Ayal Klein and Jonathan Mamou and Valentina Pyatkin and Weiss, {Daniela Brook} and Hangfeng He and Dan Roth and Luke Zettlemoyer and Ido Dagan",

note = "Publisher Copyright: {\textcopyright} 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.; 28th International Conference on Computational Linguistics, COLING 2020 ; Conference date: 08-12-2020 Through 13-12-2020",

year = "2020",

language = "אנגלית",

series = "COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference",

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

pages = "3069--3083",

editor = "Donia Scott and Nuria Bel and Chengqing Zong",

booktitle = "COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference",

address = "ארצות הברית",

}

Klein, A, Mamou, J, Pyatkin, V, Weiss, DB, He, H, Roth, D, Zettlemoyer, L & Dagan, I 2020, QANom: Question-Answer driven SRL for Nominalizations. in D Scott, N Bel & C Zong (eds), COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 3069-3083, 28th International Conference on Computational Linguistics, COLING 2020, Virtual, Online, Spain, 8/12/20.

QANom: Question-Answer driven SRL for Nominalizations. / Klein, Ayal; Mamou, Jonathan; Pyatkin, Valentina et al.
COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. ed. / Donia Scott; Nuria Bel; Chengqing Zong. Association for Computational Linguistics (ACL), 2020. p. 3069-3083 (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference).

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

TY - GEN

T1 - QANom

T2 - 28th International Conference on Computational Linguistics, COLING 2020

AU - Klein, Ayal

AU - Mamou, Jonathan

AU - Pyatkin, Valentina

AU - Weiss, Daniela Brook

AU - He, Hangfeng

AU - Roth, Dan

AU - Zettlemoyer, Luke

AU - Dagan, Ido

PY - 2020

Y1 - 2020

N2 - We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.

AB - We propose a new semantic scheme for capturing predicate-argument relations for nominalizations, termed QANom. This scheme extends the QA-SRL formalism (He et al., 2015), modeling the relations between nominalizations and their arguments via natural language question-answer pairs. We construct the first QANom dataset using controlled crowdsourcing, analyze its quality and compare it to expertly annotated nominal-SRL annotations, as well as to other QA-driven annotations. In addition, we train a baseline QANom parser for identifying nominalizations and labeling their arguments with question-answer pairs. Finally, we demonstrate the extrinsic utility of our annotations for downstream tasks using both indirect supervision and zero-shot settings.

UR - http://www.scopus.com/inward/record.url?scp=85115674964&partnerID=8YFLogxK

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

T3 - COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

SP - 3069

EP - 3083

BT - COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference

A2 - Scott, Donia

A2 - Bel, Nuria

A2 - Zong, Chengqing

PB - Association for Computational Linguistics (ACL)

Y2 - 8 December 2020 through 13 December 2020

ER -

Klein A, Mamou J, Pyatkin V, Weiss DB, He H, Roth D et al. QANom: Question-Answer driven SRL for Nominalizations. In Scott D, Bel N, Zong C, editors, COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2020. p. 3069-3083. (COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference).

QANom: Question-Answer driven SRL for Nominalizations

Abstract

Publication series

Conference

Bibliographical note

Funding

Other files and links

Fingerprint

Cite this