Modeling skip-grams for event detection with convolutional neural networks

Thien Huu Nguyen, Ralph Grishman

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

Abstract

Convolutional neural networks (CNN) have achieved the top performance for event detection due to their capacity to induce the underlying structures of the k-grams in the sentences. However, the current CNN-based event detectors only model the consecutive k-grams and ignore the non-consecutive kgrams that might involve important structures for event detection. In this work, we propose to improve the current CNN models for ED by introducing the non-consecutive convolution. Our systematic evaluation on both the general setting and the domain adaptation setting demonstrates the effectiveness of the nonconsecutive CNN model, leading to the significant performance improvement over the current state-of-the-art systems.

Original languageEnglish (US)
Title of host publicationEMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings
PublisherAssociation for Computational Linguistics (ACL)
Pages886-891
Number of pages6
ISBN (Electronic)9781945626258
StatePublished - Jan 1 2016
Event2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016 - Austin, United States
Duration: Nov 1 2016Nov 5 2016

Publication series

NameEMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

Conference

Conference2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016
CountryUnited States
CityAustin
Period11/1/1611/5/16

Fingerprint

Neural networks
Convolution
Detectors

ASJC Scopus subject areas

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

Cite this

Nguyen, T. H., & Grishman, R. (2016). Modeling skip-grams for event detection with convolutional neural networks. In EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings (pp. 886-891). (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings). Association for Computational Linguistics (ACL).

Modeling skip-grams for event detection with convolutional neural networks. / Nguyen, Thien Huu; Grishman, Ralph.

EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2016. p. 886-891 (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings).

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

Nguyen, TH & Grishman, R 2016, Modeling skip-grams for event detection with convolutional neural networks. in EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings. EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings, Association for Computational Linguistics (ACL), pp. 886-891, 2016 Conference on Empirical Methods in Natural Language Processing, EMNLP 2016, Austin, United States, 11/1/16.
Nguyen TH, Grishman R. Modeling skip-grams for event detection with convolutional neural networks. In EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL). 2016. p. 886-891. (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
Nguyen, Thien Huu ; Grishman, Ralph. / Modeling skip-grams for event detection with convolutional neural networks. EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings. Association for Computational Linguistics (ACL), 2016. pp. 886-891 (EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings).
@inproceedings{7798c185477b4d558abb057262f24df1,
title = "Modeling skip-grams for event detection with convolutional neural networks",
abstract = "Convolutional neural networks (CNN) have achieved the top performance for event detection due to their capacity to induce the underlying structures of the k-grams in the sentences. However, the current CNN-based event detectors only model the consecutive k-grams and ignore the non-consecutive kgrams that might involve important structures for event detection. In this work, we propose to improve the current CNN models for ED by introducing the non-consecutive convolution. Our systematic evaluation on both the general setting and the domain adaptation setting demonstrates the effectiveness of the nonconsecutive CNN model, leading to the significant performance improvement over the current state-of-the-art systems.",
author = "Nguyen, {Thien Huu} and Ralph Grishman",
year = "2016",
month = "1",
day = "1",
language = "English (US)",
series = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings",
publisher = "Association for Computational Linguistics (ACL)",
pages = "886--891",
booktitle = "EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings",

}

TY - GEN

T1 - Modeling skip-grams for event detection with convolutional neural networks

AU - Nguyen, Thien Huu

AU - Grishman, Ralph

PY - 2016/1/1

Y1 - 2016/1/1

N2 - Convolutional neural networks (CNN) have achieved the top performance for event detection due to their capacity to induce the underlying structures of the k-grams in the sentences. However, the current CNN-based event detectors only model the consecutive k-grams and ignore the non-consecutive kgrams that might involve important structures for event detection. In this work, we propose to improve the current CNN models for ED by introducing the non-consecutive convolution. Our systematic evaluation on both the general setting and the domain adaptation setting demonstrates the effectiveness of the nonconsecutive CNN model, leading to the significant performance improvement over the current state-of-the-art systems.

AB - Convolutional neural networks (CNN) have achieved the top performance for event detection due to their capacity to induce the underlying structures of the k-grams in the sentences. However, the current CNN-based event detectors only model the consecutive k-grams and ignore the non-consecutive kgrams that might involve important structures for event detection. In this work, we propose to improve the current CNN models for ED by introducing the non-consecutive convolution. Our systematic evaluation on both the general setting and the domain adaptation setting demonstrates the effectiveness of the nonconsecutive CNN model, leading to the significant performance improvement over the current state-of-the-art systems.

UR - http://www.scopus.com/inward/record.url?scp=85031409529&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85031409529&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85031409529

T3 - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

SP - 886

EP - 891

BT - EMNLP 2016 - Conference on Empirical Methods in Natural Language Processing, Proceedings

PB - Association for Computational Linguistics (ACL)

ER -