Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model

Vered Shwartz; Chris Waterson

Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model

Vered Shwartz, Chris Waterson

Department of Computer Science

Alphabet Inc.

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

22 Scopus citations

Abstract

Automatic interpretation of the relation between the constituents of a noun compound, e.g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications. Recent approaches are typically based on either noun-compound representations or paraphrases. While the former has initially shown promising results, recent work suggests that the success stems from memorizing single prototypical words for each relation. We explore a neural paraphrasing approach that demonstrates superior performance when such memorization is not possible.

Original language	English
Title of host publication	Short Papers
Publisher	Association for Computational Linguistics (ACL)
Pages	218-224
Number of pages	7
ISBN (Electronic)	9781948087292
State	Published - 2018
Event	2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 - New Orleans, United States Duration: 1 Jun 2018 → 6 Jun 2018

Publication series

Name	NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference
Volume	2

Conference

Conference	2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018
Country/Territory	United States
City	New Orleans
Period	1/06/18 → 6/06/18

Bibliographical note

Publisher Copyright:
© 2018 Association for Computational Linguistics.

Cite this

Shwartz, V., & Waterson, C. (2018). Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model. In Short Papers (pp. 218-224). (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; Vol. 2). Association for Computational Linguistics (ACL).

Shwartz, Vered ; Waterson, Chris. / Olive oil is made of olives, baby oil is made for babies : Interpreting noun compounds using paraphrases in a neural model. Short Papers. Association for Computational Linguistics (ACL), 2018. pp. 218-224 (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference).

@inproceedings{1f86fe6e64494d549c8909341c4f9519,

title = "Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model",

abstract = "Automatic interpretation of the relation between the constituents of a noun compound, e.g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications. Recent approaches are typically based on either noun-compound representations or paraphrases. While the former has initially shown promising results, recent work suggests that the success stems from memorizing single prototypical words for each relation. We explore a neural paraphrasing approach that demonstrates superior performance when such memorization is not possible.",

author = "Vered Shwartz and Chris Waterson",

note = "Publisher Copyright: {\textcopyright} 2018 Association for Computational Linguistics.; 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018 ; Conference date: 01-06-2018 Through 06-06-2018",

year = "2018",

language = "אנגלית",

series = "NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference",

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

pages = "218--224",

booktitle = "Short Papers",

address = "ארצות הברית",

}

Shwartz, V & Waterson, C 2018, Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model. in Short Papers. NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 2, Association for Computational Linguistics (ACL), pp. 218-224, 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018, New Orleans, United States, 1/06/18.

Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model. / Shwartz, Vered; Waterson, Chris.
Short Papers. Association for Computational Linguistics (ACL), 2018. p. 218-224 (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference; Vol. 2).

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

TY - GEN

T1 - Olive oil is made of olives, baby oil is made for babies

T2 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL HLT 2018

AU - Shwartz, Vered

AU - Waterson, Chris

PY - 2018

Y1 - 2018

N2 - Automatic interpretation of the relation between the constituents of a noun compound, e.g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications. Recent approaches are typically based on either noun-compound representations or paraphrases. While the former has initially shown promising results, recent work suggests that the success stems from memorizing single prototypical words for each relation. We explore a neural paraphrasing approach that demonstrates superior performance when such memorization is not possible.

AB - Automatic interpretation of the relation between the constituents of a noun compound, e.g. olive oil (source) and baby oil (purpose) is an important task for many NLP applications. Recent approaches are typically based on either noun-compound representations or paraphrases. While the former has initially shown promising results, recent work suggests that the success stems from memorizing single prototypical words for each relation. We explore a neural paraphrasing approach that demonstrates superior performance when such memorization is not possible.

UR - http://www.scopus.com/inward/record.url?scp=85077760423&partnerID=8YFLogxK

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

AN - SCOPUS:85077760423

T3 - NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference

SP - 218

EP - 224

BT - Short Papers

PB - Association for Computational Linguistics (ACL)

Y2 - 1 June 2018 through 6 June 2018

ER -

Shwartz V, Waterson C. Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model. In Short Papers. Association for Computational Linguistics (ACL). 2018. p. 218-224. (NAACL HLT 2018 - 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference).

Olive oil is made of olives, baby oil is made for babies: Interpreting noun compounds using paraphrases in a neural model

Abstract

Publication series

Conference

Bibliographical note

Other files and links

Fingerprint

Cite this