Improving hypernymy detection with an integrated path-based and distributional method

Vered Shwartz; Yoav Goldberg; Ido Dagan

doi:10.18653/v1/p16-1226

Improving hypernymy detection with an integrated path-based and distributional method

Vered Shwartz, Yoav Goldberg, Ido Dagan

Department of Computer Science

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

153 Scopus citations

Abstract

Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.

Original language	English
Title of host publication	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	2389-2398
Number of pages	10
ISBN (Electronic)	9781510827585
DOIs	https://doi.org/10.18653/v1/p16-1226
State	Published - 2016
Event	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Berlin, Germany Duration: 7 Aug 2016 → 12 Aug 2016

Publication series

Name	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers
Volume	4

Conference

Conference	54th Annual Meeting of the Association for Computational Linguistics, ACL 2016
Country/Territory	Germany
City	Berlin
Period	7/08/16 → 12/08/16

Bibliographical note

Publisher Copyright:
© 2016 Association for Computational Linguistics.

Funding

We would like to thank Omer Levy for his involvement and assistance in the early stage of this project and Enrico Santus for helping us by computing the results of SLQS (Santus et al, 2014) on our dataset. This work was partially supported by an Intel ICRI-CI grant, the Israel Science Foundation grant 880/12, 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 ICRI-CI
Deutsche Forschungsgemeinschaft
Israel Science Foundation	880/12

Access to Document

10.18653/v1/p16-1226

Cite this

Shwartz, V., Goldberg, Y., & Dagan, I. (2016). Improving hypernymy detection with an integrated path-based and distributional method. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers (pp. 2389-2398). (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 4). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/p16-1226

Shwartz, Vered ; Goldberg, Yoav ; Dagan, Ido. / Improving hypernymy detection with an integrated path-based and distributional method. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), 2016. pp. 2389-2398 (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers).

@inproceedings{d0f52d0c55754994b4489b96619df86a,

title = "Improving hypernymy detection with an integrated path-based and distributional method",

abstract = "Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.",

author = "Vered Shwartz and Yoav Goldberg and Ido Dagan",

note = "Publisher Copyright: {\textcopyright} 2016 Association for Computational Linguistics.; 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 ; Conference date: 07-08-2016 Through 12-08-2016",

year = "2016",

doi = "10.18653/v1/p16-1226",

language = "אנגלית",

series = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",

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

pages = "2389--2398",

booktitle = "54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers",

address = "ארצות הברית",

}

Shwartz, V, Goldberg, Y & Dagan, I 2016, Improving hypernymy detection with an integrated path-based and distributional method. in 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers, vol. 4, Association for Computational Linguistics (ACL), pp. 2389-2398, 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016, Berlin, Germany, 7/08/16. https://doi.org/10.18653/v1/p16-1226

Improving hypernymy detection with an integrated path-based and distributional method. / Shwartz, Vered; Goldberg, Yoav ; Dagan, Ido.
54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL), 2016. p. 2389-2398 (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers; Vol. 4).

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

TY - GEN

T1 - Improving hypernymy detection with an integrated path-based and distributional method

AU - Shwartz, Vered

AU - Goldberg, Yoav

AU - Dagan, Ido

PY - 2016

Y1 - 2016

N2 - Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.

AB - Detecting hypernymy relations is a key task in NLP, which is addressed in the literature using two complementary approaches. Distributional methods, whose supervised variants are the current best performers, and path-based methods, which received less research attention. We suggest an improved path-based algorithm, in which the dependency paths are encoded using a recurrent neural network, that achieves results comparable to distributional methods. We then extend the approach to integrate both path-based and distributional signals, significantly improving upon the state-of-the-art on this task.

UR - http://www.scopus.com/inward/record.url?scp=85011967258&partnerID=8YFLogxK

U2 - 10.18653/v1/p16-1226

DO - 10.18653/v1/p16-1226

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

AN - SCOPUS:85011967258

T3 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

SP - 2389

EP - 2398

BT - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers

PB - Association for Computational Linguistics (ACL)

T2 - 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016

Y2 - 7 August 2016 through 12 August 2016

ER -

Shwartz V, Goldberg Y , Dagan I. Improving hypernymy detection with an integrated path-based and distributional method. In 54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers. Association for Computational Linguistics (ACL). 2016. p. 2389-2398. (54th Annual Meeting of the Association for Computational Linguistics, ACL 2016 - Long Papers). doi: 10.18653/v1/p16-1226

Improving hypernymy detection with an integrated path-based and distributional method

Abstract

Publication series

Conference

Bibliographical note

Funding

Access to Document

Other files and links

Fingerprint

Cite this