Inducing example-based semantic frames from a massive amount of verb uses

Daisuke Kawahara, Daniel W. Peterson, Octavian Popescu, Martha Palmer

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

10 Citations (Scopus)

Abstract

We present an unsupervised method for inducing semantic frames from verb uses in giga-word corpora. Our semantic frames are verb-specific example-based frames that are distinguished according to their senses. We use the Chinese Restaurant Process to automatically induce these frames from a massive amount of verb instances. In our experiments, we acquire broad-coverage semantic frames from two giga-word corpora, the larger comprising 20 billion words. Our experimental results indicate the effectiveness of our approach.

Original languageEnglish
Title of host publication14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014
PublisherAssociation for Computational Linguistics (ACL)
Pages58-67
Number of pages10
ISBN (Print)9781632663962
Publication statusPublished - Jan 1 2014
Event14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014 - Gothenburg, Sweden
Duration: Apr 26 2014Apr 30 2014

Publication series

Name14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014

Other

Other14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014
CountrySweden
CityGothenburg
Period4/26/144/30/14

Fingerprint

Semantics
Experiments

All Science Journal Classification (ASJC) codes

  • Software

Cite this

Kawahara, D., Peterson, D. W., Popescu, O., & Palmer, M. (2014). Inducing example-based semantic frames from a massive amount of verb uses. In 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014 (pp. 58-67). (14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014). Association for Computational Linguistics (ACL).

Inducing example-based semantic frames from a massive amount of verb uses. / Kawahara, Daisuke; Peterson, Daniel W.; Popescu, Octavian; Palmer, Martha.

14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014. Association for Computational Linguistics (ACL), 2014. p. 58-67 (14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014).

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

Kawahara, D, Peterson, DW, Popescu, O & Palmer, M 2014, Inducing example-based semantic frames from a massive amount of verb uses. in 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014. 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014, Association for Computational Linguistics (ACL), pp. 58-67, 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014, Gothenburg, Sweden, 4/26/14.
Kawahara D, Peterson DW, Popescu O, Palmer M. Inducing example-based semantic frames from a massive amount of verb uses. In 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014. Association for Computational Linguistics (ACL). 2014. p. 58-67. (14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014).
Kawahara, Daisuke ; Peterson, Daniel W. ; Popescu, Octavian ; Palmer, Martha. / Inducing example-based semantic frames from a massive amount of verb uses. 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014. Association for Computational Linguistics (ACL), 2014. pp. 58-67 (14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014).
@inproceedings{88262b4404604da9abab9113814f5025,
title = "Inducing example-based semantic frames from a massive amount of verb uses",
abstract = "We present an unsupervised method for inducing semantic frames from verb uses in giga-word corpora. Our semantic frames are verb-specific example-based frames that are distinguished according to their senses. We use the Chinese Restaurant Process to automatically induce these frames from a massive amount of verb instances. In our experiments, we acquire broad-coverage semantic frames from two giga-word corpora, the larger comprising 20 billion words. Our experimental results indicate the effectiveness of our approach.",
author = "Daisuke Kawahara and Peterson, {Daniel W.} and Octavian Popescu and Martha Palmer",
year = "2014",
month = "1",
day = "1",
language = "English",
isbn = "9781632663962",
series = "14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014",
publisher = "Association for Computational Linguistics (ACL)",
pages = "58--67",
booktitle = "14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014",

}

TY - GEN

T1 - Inducing example-based semantic frames from a massive amount of verb uses

AU - Kawahara, Daisuke

AU - Peterson, Daniel W.

AU - Popescu, Octavian

AU - Palmer, Martha

PY - 2014/1/1

Y1 - 2014/1/1

N2 - We present an unsupervised method for inducing semantic frames from verb uses in giga-word corpora. Our semantic frames are verb-specific example-based frames that are distinguished according to their senses. We use the Chinese Restaurant Process to automatically induce these frames from a massive amount of verb instances. In our experiments, we acquire broad-coverage semantic frames from two giga-word corpora, the larger comprising 20 billion words. Our experimental results indicate the effectiveness of our approach.

AB - We present an unsupervised method for inducing semantic frames from verb uses in giga-word corpora. Our semantic frames are verb-specific example-based frames that are distinguished according to their senses. We use the Chinese Restaurant Process to automatically induce these frames from a massive amount of verb instances. In our experiments, we acquire broad-coverage semantic frames from two giga-word corpora, the larger comprising 20 billion words. Our experimental results indicate the effectiveness of our approach.

UR - http://www.scopus.com/inward/record.url?scp=84905689474&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84905689474&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84905689474

SN - 9781632663962

T3 - 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014

SP - 58

EP - 67

BT - 14th Conference of the European Chapter of the Association for Computational Linguistics 2014, EACL 2014

PB - Association for Computational Linguistics (ACL)

ER -