Solving relational similarity problems using the web as a corpus

Preslav Nakov, Marti A. Hearst

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

40 Citations (Scopus)

Abstract

We present a simple linguistically-motivated method for characterizing the semantic relations that hold between two nouns. The approach leverages the vast size of the Web in order to build lexically-specific features. The main idea is to look for verbs, prepositions, and coordinating conjunctions that can help make explicit the hidden relations between the target nouns. Using these features in instance-based classifiers, we demonstrate state-of-the-art results on various relational similarity problems, including mapping noun-modifier pairs to abstract relations like TIME, LOCATION and CONTAINER, characterizing noun-noun compounds in terms of abstract linguistic predicates like CAUSE, USE, and FROM, classifying the relations between nominals in context, and solving SAT verbal analogy problems. In essence, the approach puts together some existing ideas, showing that they apply generally to various semantic tasks, finding that verbs are especially useful features.

Original languageEnglish
Title of host publicationACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference
Pages452-460
Number of pages9
Publication statusPublished - 1 Dec 2008
Externally publishedYes
Event46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT - Columbus, OH, United States
Duration: 15 Jun 200820 Jun 2008

Other

Other46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT
CountryUnited States
CityColumbus, OH
Period15/6/0820/6/08

Fingerprint

Semantics
semantics
Linguistics
Classifiers
linguistics
Nouns
World Wide Web
Verbs
Coordinating Conjunction
Prepositions
Classifier
Nominals
Noun-noun Compounds
Modifier
Satisfiability
Semantic Relations
Essence

ASJC Scopus subject areas

  • Language and Linguistics
  • Computer Networks and Communications
  • Linguistics and Language

Cite this

Nakov, P., & Hearst, M. A. (2008). Solving relational similarity problems using the web as a corpus. In ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference (pp. 452-460)

Solving relational similarity problems using the web as a corpus. / Nakov, Preslav; Hearst, Marti A.

ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. p. 452-460.

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

Nakov, P & Hearst, MA 2008, Solving relational similarity problems using the web as a corpus. in ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. pp. 452-460, 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, ACL-08: HLT, Columbus, OH, United States, 15/6/08.
Nakov P, Hearst MA. Solving relational similarity problems using the web as a corpus. In ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. p. 452-460
Nakov, Preslav ; Hearst, Marti A. / Solving relational similarity problems using the web as a corpus. ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference. 2008. pp. 452-460
@inproceedings{67ade2ea736748da90fd4459730dbaa7,
title = "Solving relational similarity problems using the web as a corpus",
abstract = "We present a simple linguistically-motivated method for characterizing the semantic relations that hold between two nouns. The approach leverages the vast size of the Web in order to build lexically-specific features. The main idea is to look for verbs, prepositions, and coordinating conjunctions that can help make explicit the hidden relations between the target nouns. Using these features in instance-based classifiers, we demonstrate state-of-the-art results on various relational similarity problems, including mapping noun-modifier pairs to abstract relations like TIME, LOCATION and CONTAINER, characterizing noun-noun compounds in terms of abstract linguistic predicates like CAUSE, USE, and FROM, classifying the relations between nominals in context, and solving SAT verbal analogy problems. In essence, the approach puts together some existing ideas, showing that they apply generally to various semantic tasks, finding that verbs are especially useful features.",
author = "Preslav Nakov and Hearst, {Marti A.}",
year = "2008",
month = "12",
day = "1",
language = "English",
isbn = "9781932432046",
pages = "452--460",
booktitle = "ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference",

}

TY - GEN

T1 - Solving relational similarity problems using the web as a corpus

AU - Nakov, Preslav

AU - Hearst, Marti A.

PY - 2008/12/1

Y1 - 2008/12/1

N2 - We present a simple linguistically-motivated method for characterizing the semantic relations that hold between two nouns. The approach leverages the vast size of the Web in order to build lexically-specific features. The main idea is to look for verbs, prepositions, and coordinating conjunctions that can help make explicit the hidden relations between the target nouns. Using these features in instance-based classifiers, we demonstrate state-of-the-art results on various relational similarity problems, including mapping noun-modifier pairs to abstract relations like TIME, LOCATION and CONTAINER, characterizing noun-noun compounds in terms of abstract linguistic predicates like CAUSE, USE, and FROM, classifying the relations between nominals in context, and solving SAT verbal analogy problems. In essence, the approach puts together some existing ideas, showing that they apply generally to various semantic tasks, finding that verbs are especially useful features.

AB - We present a simple linguistically-motivated method for characterizing the semantic relations that hold between two nouns. The approach leverages the vast size of the Web in order to build lexically-specific features. The main idea is to look for verbs, prepositions, and coordinating conjunctions that can help make explicit the hidden relations between the target nouns. Using these features in instance-based classifiers, we demonstrate state-of-the-art results on various relational similarity problems, including mapping noun-modifier pairs to abstract relations like TIME, LOCATION and CONTAINER, characterizing noun-noun compounds in terms of abstract linguistic predicates like CAUSE, USE, and FROM, classifying the relations between nominals in context, and solving SAT verbal analogy problems. In essence, the approach puts together some existing ideas, showing that they apply generally to various semantic tasks, finding that verbs are especially useful features.

UR - http://www.scopus.com/inward/record.url?scp=84859913003&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84859913003&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84859913003

SN - 9781932432046

SP - 452

EP - 460

BT - ACL-08: HLT - 46th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies, Proceedings of the Conference

ER -