Event detection and domain adaptation with convolutional neural networks

Thien Huu Nguyen, Ralph Grishman

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

Abstract

We study the event detection problem us-ing convolutional neural networks (CNNs) that overcome the two fundamental limi-tations of the traditional feature-based ap-proaches to this task: complicated feature engineering for rich feature sets and er-ror propagation from the preceding stages which generate these features. The experi-mental results show that the CNNs outper-form the best reported feature-based sys-tems in the general setting as well as the domain adaptation setting without resort-ing to extensive external resources.

Original languageEnglish (US)
Title of host publicationACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference
PublisherAssociation for Computational Linguistics (ACL)
Pages365-371
Number of pages7
Volume2
ISBN (Print)9781941643730
StatePublished - 2015
Event53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015 - Beijing, China
Duration: Jul 26 2015Jul 31 2015

Other

Other53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015
CountryChina
CityBeijing
Period7/26/157/31/15

Fingerprint

Neural networks

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software

Cite this

Nguyen, T. H., & Grishman, R. (2015). Event detection and domain adaptation with convolutional neural networks. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 2, pp. 365-371). Association for Computational Linguistics (ACL).

Event detection and domain adaptation with convolutional neural networks. / Nguyen, Thien Huu; Grishman, Ralph.

ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2015. p. 365-371.

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

Nguyen, TH & Grishman, R 2015, Event detection and domain adaptation with convolutional neural networks. in ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. vol. 2, Association for Computational Linguistics (ACL), pp. 365-371, 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, ACL-IJCNLP 2015, Beijing, China, 7/26/15.
Nguyen TH, Grishman R. Event detection and domain adaptation with convolutional neural networks. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 2. Association for Computational Linguistics (ACL). 2015. p. 365-371
Nguyen, Thien Huu ; Grishman, Ralph. / Event detection and domain adaptation with convolutional neural networks. ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference. Vol. 2 Association for Computational Linguistics (ACL), 2015. pp. 365-371
@inproceedings{3838e6bd88194c0287c3d76663a68271,
title = "Event detection and domain adaptation with convolutional neural networks",
abstract = "We study the event detection problem us-ing convolutional neural networks (CNNs) that overcome the two fundamental limi-tations of the traditional feature-based ap-proaches to this task: complicated feature engineering for rich feature sets and er-ror propagation from the preceding stages which generate these features. The experi-mental results show that the CNNs outper-form the best reported feature-based sys-tems in the general setting as well as the domain adaptation setting without resort-ing to extensive external resources.",
author = "Nguyen, {Thien Huu} and Ralph Grishman",
year = "2015",
language = "English (US)",
isbn = "9781941643730",
volume = "2",
pages = "365--371",
booktitle = "ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference",
publisher = "Association for Computational Linguistics (ACL)",

}

TY - GEN

T1 - Event detection and domain adaptation with convolutional neural networks

AU - Nguyen, Thien Huu

AU - Grishman, Ralph

PY - 2015

Y1 - 2015

N2 - We study the event detection problem us-ing convolutional neural networks (CNNs) that overcome the two fundamental limi-tations of the traditional feature-based ap-proaches to this task: complicated feature engineering for rich feature sets and er-ror propagation from the preceding stages which generate these features. The experi-mental results show that the CNNs outper-form the best reported feature-based sys-tems in the general setting as well as the domain adaptation setting without resort-ing to extensive external resources.

AB - We study the event detection problem us-ing convolutional neural networks (CNNs) that overcome the two fundamental limi-tations of the traditional feature-based ap-proaches to this task: complicated feature engineering for rich feature sets and er-ror propagation from the preceding stages which generate these features. The experi-mental results show that the CNNs outper-form the best reported feature-based sys-tems in the general setting as well as the domain adaptation setting without resort-ing to extensive external resources.

UR - http://www.scopus.com/inward/record.url?scp=84944030435&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84944030435&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:84944030435

SN - 9781941643730

VL - 2

SP - 365

EP - 371

BT - ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference

PB - Association for Computational Linguistics (ACL)

ER -