Integrating deep linguistic features in factuality prediction over unified datasets

Gabriel Stanovsky; Judith Eckle-Kohler; Yevgeniy Puzikov; Ido Dagan; Iryna Gurevych

doi:10.18653/v1/P17-2056

Integrating deep linguistic features in factuality prediction over unified datasets

Gabriel Stanovsky, Judith Eckle-Kohler, Yevgeniy Puzikov, Ido Dagan, Iryna Gurevych

Department of Computer Science

Technische Universität Darmstadt

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

35 Scopus citations

Abstract

Previous models for the assessment of commitment towards a predicate in a sentence (also known as factuality prediction) were trained and tested against a specific annotated dataset, subsequently limiting the generality of their results. In this work we propose an intuitive method for mapping three previously annotated corpora onto a single factuality scale, thereby enabling models to be tested across these corpora. In addition, we design a novel model for factuality prediction by first extending a previous rule-based factuality prediction system and applying it over an abstraction of dependency trees, and then using the output of this system in a supervised classifier. We show that this model outperforms previous methods on all three datasets. We make both the unified factuality corpus and our new model publicly available.

Original language	English
Title of host publication	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)
Publisher	Association for Computational Linguistics (ACL)
Pages	352-357
Number of pages	6
ISBN (Electronic)	9781945626760
DOIs	https://doi.org/10.18653/v1/P17-2056
State	Published - 2017
Event	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 - Vancouver, Canada Duration: 30 Jul 2017 → 4 Aug 2017

Publication series

Name	ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)
Volume	2

Conference

Conference	55th Annual Meeting of the Association for Computational Linguistics, ACL 2017
Country/Territory	Canada
City	Vancouver
Period	30/07/17 → 4/08/17

Bibliographical note

Publisher Copyright:
© 2017 Association for Computational Linguistics.

Funding

We would like to thank the anonymous reviewers for their helpful comments. This work was supported in part by grants from the MAGNET program of the Israeli Office of the Chief Scientist (OCS) and by 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
Israeli Office of the Chief Scientist
Deutsche Forschungsgemeinschaft
Oncosuisse
Office of the Chief Scientist, Ministry of Economy

Access to Document

10.18653/v1/P17-2056

Cite this

Stanovsky, G., Eckle-Kohler, J., Puzikov, Y., Dagan, I., & Gurevych, I. (2017). Integrating deep linguistic features in factuality prediction over unified datasets. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers) (pp. 352-357). (ACL 2017 - 55th 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/P17-2056

Stanovsky, Gabriel ; Eckle-Kohler, Judith ; Puzikov, Yevgeniy et al. / Integrating deep linguistic features in factuality prediction over unified datasets. ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2017. pp. 352-357 (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)).

@inproceedings{253453a79ad84e1d863f7eebb819545c,

title = "Integrating deep linguistic features in factuality prediction over unified datasets",

abstract = "Previous models for the assessment of commitment towards a predicate in a sentence (also known as factuality prediction) were trained and tested against a specific annotated dataset, subsequently limiting the generality of their results. In this work we propose an intuitive method for mapping three previously annotated corpora onto a single factuality scale, thereby enabling models to be tested across these corpora. In addition, we design a novel model for factuality prediction by first extending a previous rule-based factuality prediction system and applying it over an abstraction of dependency trees, and then using the output of this system in a supervised classifier. We show that this model outperforms previous methods on all three datasets. We make both the unified factuality corpus and our new model publicly available.",

author = "Gabriel Stanovsky and Judith Eckle-Kohler and Yevgeniy Puzikov and Ido Dagan and Iryna Gurevych",

note = "Publisher Copyright: {\textcopyright} 2017 Association for Computational Linguistics.; 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017 ; Conference date: 30-07-2017 Through 04-08-2017",

year = "2017",

doi = "10.18653/v1/P17-2056",

language = "אנגלית",

series = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)",

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

pages = "352--357",

booktitle = "ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)",

address = "ארצות הברית",

}

Stanovsky, G, Eckle-Kohler, J, Puzikov, Y, Dagan, I & Gurevych, I 2017, Integrating deep linguistic features in factuality prediction over unified datasets. in ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers), vol. 2, Association for Computational Linguistics (ACL), pp. 352-357, 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017, Vancouver, Canada, 30/07/17. https://doi.org/10.18653/v1/P17-2056

Integrating deep linguistic features in factuality prediction over unified datasets. / Stanovsky, Gabriel; Eckle-Kohler, Judith; Puzikov, Yevgeniy et al.
ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL), 2017. p. 352-357 (ACL 2017 - 55th 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 - Integrating deep linguistic features in factuality prediction over unified datasets

AU - Stanovsky, Gabriel

AU - Eckle-Kohler, Judith

AU - Puzikov, Yevgeniy

AU - Dagan, Ido

AU - Gurevych, Iryna

PY - 2017

Y1 - 2017

N2 - Previous models for the assessment of commitment towards a predicate in a sentence (also known as factuality prediction) were trained and tested against a specific annotated dataset, subsequently limiting the generality of their results. In this work we propose an intuitive method for mapping three previously annotated corpora onto a single factuality scale, thereby enabling models to be tested across these corpora. In addition, we design a novel model for factuality prediction by first extending a previous rule-based factuality prediction system and applying it over an abstraction of dependency trees, and then using the output of this system in a supervised classifier. We show that this model outperforms previous methods on all three datasets. We make both the unified factuality corpus and our new model publicly available.

AB - Previous models for the assessment of commitment towards a predicate in a sentence (also known as factuality prediction) were trained and tested against a specific annotated dataset, subsequently limiting the generality of their results. In this work we propose an intuitive method for mapping three previously annotated corpora onto a single factuality scale, thereby enabling models to be tested across these corpora. In addition, we design a novel model for factuality prediction by first extending a previous rule-based factuality prediction system and applying it over an abstraction of dependency trees, and then using the output of this system in a supervised classifier. We show that this model outperforms previous methods on all three datasets. We make both the unified factuality corpus and our new model publicly available.

UR - http://www.scopus.com/inward/record.url?scp=85040561681&partnerID=8YFLogxK

U2 - 10.18653/v1/P17-2056

DO - 10.18653/v1/P17-2056

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

AN - SCOPUS:85040561681

T3 - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)

SP - 352

EP - 357

BT - ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers)

PB - Association for Computational Linguistics (ACL)

T2 - 55th Annual Meeting of the Association for Computational Linguistics, ACL 2017

Y2 - 30 July 2017 through 4 August 2017

ER -

Stanovsky G, Eckle-Kohler J, Puzikov Y, Dagan I, Gurevych I. Integrating deep linguistic features in factuality prediction over unified datasets. In ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Short Papers). Association for Computational Linguistics (ACL). 2017. p. 352-357. (ACL 2017 - 55th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (Long Papers)). doi: 10.18653/v1/P17-2056

Integrating deep linguistic features in factuality prediction over unified datasets

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this