The effectiveness of simple hybrid systems for hypernym discovery

William Held; Nizar Habash

The effectiveness of simple hybrid systems for hypernym discovery

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

Abstract

Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods. However, recent works utilizing a mix of these strategies have yielded state-of-the-art results. This paper evaluates the contribution of both paradigms to hybrid success by evaluating the benefits of hybrid treatment of baseline models from each paradigm. Even with a simple methodology for each individual system, utilizing a hybrid approach establishes new state-of-the-art results on two domain-specific English hypernym discovery tasks and outperforms all non-hybrid approaches in a general English hypernym discovery task.

Original language	English (US)
Title of host publication	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference
Publisher	Association for Computational Linguistics (ACL)
Pages	3362-3367
Number of pages	6
ISBN (Electronic)	9781950737482
State	Published - 2019
Event	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 - Florence, Italy Duration: Jul 28 2019 → Aug 2 2019

Publication series

Name	ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

Conference

Conference	57th Annual Meeting of the Association for Computational Linguistics, ACL 2019
Country/Territory	Italy
City	Florence
Period	7/28/19 → 8/2/19

ASJC Scopus subject areas

Language and Linguistics
General Computer Science
Linguistics and Language

Cite this

Held, W., & Habash, N. (2019). The effectiveness of simple hybrid systems for hypernym discovery. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference (pp. 3362-3367). (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference). Association for Computational Linguistics (ACL).

The effectiveness of simple hybrid systems for hypernym discovery. / Held, William; Habash, Nizar.
ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2019. p. 3362-3367 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

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

Held, W & Habash, N 2019, The effectiveness of simple hybrid systems for hypernym discovery. in ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference, Association for Computational Linguistics (ACL), pp. 3362-3367, 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019, Florence, Italy, 7/28/19.

Held W, Habash N. The effectiveness of simple hybrid systems for hypernym discovery. In ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL). 2019. p. 3362-3367. (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

Held, William ; Habash, Nizar. / The effectiveness of simple hybrid systems for hypernym discovery. ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference. Association for Computational Linguistics (ACL), 2019. pp. 3362-3367 (ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference).

@inproceedings{53f319404f0041e280832dec641bcedd,

title = "The effectiveness of simple hybrid systems for hypernym discovery",

abstract = "Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods. However, recent works utilizing a mix of these strategies have yielded state-of-the-art results. This paper evaluates the contribution of both paradigms to hybrid success by evaluating the benefits of hybrid treatment of baseline models from each paradigm. Even with a simple methodology for each individual system, utilizing a hybrid approach establishes new state-of-the-art results on two domain-specific English hypernym discovery tasks and outperforms all non-hybrid approaches in a general English hypernym discovery task.",

author = "William Held and Nizar Habash",

note = "Publisher Copyright: {\textcopyright} 2019 Association for Computational Linguistics; 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019 ; Conference date: 28-07-2019 Through 02-08-2019",

year = "2019",

language = "English (US)",

series = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

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

pages = "3362--3367",

booktitle = "ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference",

}

TY - GEN

T1 - The effectiveness of simple hybrid systems for hypernym discovery

AU - Held, William

AU - Habash, Nizar

PY - 2019

Y1 - 2019

N2 - Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods. However, recent works utilizing a mix of these strategies have yielded state-of-the-art results. This paper evaluates the contribution of both paradigms to hybrid success by evaluating the benefits of hybrid treatment of baseline models from each paradigm. Even with a simple methodology for each individual system, utilizing a hybrid approach establishes new state-of-the-art results on two domain-specific English hypernym discovery tasks and outperforms all non-hybrid approaches in a general English hypernym discovery task.

AB - Hypernymy modeling has largely been separated according to two paradigms, pattern-based methods and distributional methods. However, recent works utilizing a mix of these strategies have yielded state-of-the-art results. This paper evaluates the contribution of both paradigms to hybrid success by evaluating the benefits of hybrid treatment of baseline models from each paradigm. Even with a simple methodology for each individual system, utilizing a hybrid approach establishes new state-of-the-art results on two domain-specific English hypernym discovery tasks and outperforms all non-hybrid approaches in a general English hypernym discovery task.

UR - http://www.scopus.com/inward/record.url?scp=85084036001&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084036001&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85084036001

T3 - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

SP - 3362

EP - 3367

BT - ACL 2019 - 57th Annual Meeting of the Association for Computational Linguistics, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

T2 - 57th Annual Meeting of the Association for Computational Linguistics, ACL 2019

Y2 - 28 July 2019 through 2 August 2019

ER -

The effectiveness of simple hybrid systems for hypernym discovery

Abstract

Publication series

Conference

ASJC Scopus subject areas

Other files and links

Fingerprint

Cite this