Large-scale noun compound interpretation using bootstrapping and the web as a corpus

Su Nam Kim, Preslav Nakov

Research output: Chapter in Book/Report/Conference proceedingConference contribution

14 Citations (Scopus)

Abstract

Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., orange juice, together with suitable fine-grained semantic interpretations, e.g., squeezed from, which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.

Original languageEnglish
Title of host publicationEMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference
Pages648-658
Number of pages11
Publication statusPublished - 3 Oct 2011
Externally publishedYes
EventConference on Empirical Methods in Natural Language Processing, EMNLP 2011 - Edinburgh, United Kingdom
Duration: 27 Jul 201131 Jul 2011

Other

OtherConference on Empirical Methods in Natural Language Processing, EMNLP 2011
CountryUnited Kingdom
CityEdinburgh
Period27/7/1131/7/11

Fingerprint

Semantics
Statistics
Processing

ASJC Scopus subject areas

  • Computational Theory and Mathematics
  • Computer Science Applications
  • Information Systems

Cite this

Kim, S. N., & Nakov, P. (2011). Large-scale noun compound interpretation using bootstrapping and the web as a corpus. In EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference (pp. 648-658)

Large-scale noun compound interpretation using bootstrapping and the web as a corpus. / Kim, Su Nam; Nakov, Preslav.

EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2011. p. 648-658.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Kim, SN & Nakov, P 2011, Large-scale noun compound interpretation using bootstrapping and the web as a corpus. in EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. pp. 648-658, Conference on Empirical Methods in Natural Language Processing, EMNLP 2011, Edinburgh, United Kingdom, 27/7/11.
Kim SN, Nakov P. Large-scale noun compound interpretation using bootstrapping and the web as a corpus. In EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2011. p. 648-658
Kim, Su Nam ; Nakov, Preslav. / Large-scale noun compound interpretation using bootstrapping and the web as a corpus. EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference. 2011. pp. 648-658
@inproceedings{6e4b7961e68f4b3da01be51ae9062621,
title = "Large-scale noun compound interpretation using bootstrapping and the web as a corpus",
abstract = "Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., orange juice, together with suitable fine-grained semantic interpretations, e.g., squeezed from, which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.",
author = "Kim, {Su Nam} and Preslav Nakov",
year = "2011",
month = "10",
day = "3",
language = "English",
isbn = "1937284115",
pages = "648--658",
booktitle = "EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference",

}

TY - GEN

T1 - Large-scale noun compound interpretation using bootstrapping and the web as a corpus

AU - Kim, Su Nam

AU - Nakov, Preslav

PY - 2011/10/3

Y1 - 2011/10/3

N2 - Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., orange juice, together with suitable fine-grained semantic interpretations, e.g., squeezed from, which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.

AB - Responding to the need for semantic lexical resources in natural language processing applications, we examine methods to acquire noun compounds (NCs), e.g., orange juice, together with suitable fine-grained semantic interpretations, e.g., squeezed from, which are directly usable as paraphrases. We employ bootstrapping and web statistics, and utilize the relationship between NCs and paraphrasing patterns to jointly extract NCs and such patterns in multiple alternating iterations. In evaluation, we found that having one compound noun fixed yields both a higher number of semantically interpreted NCs and improved accuracy due to stronger semantic restrictions.

UR - http://www.scopus.com/inward/record.url?scp=80053235415&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=80053235415&partnerID=8YFLogxK

M3 - Conference contribution

SN - 1937284115

SN - 9781937284114

SP - 648

EP - 658

BT - EMNLP 2011 - Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference

ER -