Graph convolutional networks with argument-aware pooling for event detection

Thien Huu Nguyen, Ralph Grishman

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

Abstract

The current neural network models for event detection have only considered the sequential representation of sentences. Syntactic representations have not been explored in this area although they provide an effective mechanism to directly link words to their informative context for event detection in the sentences. In this work, we investigate a convolutional neural network based on dependency trees to perform event detection. We propose a novel pooling method that relies on entity mentions to aggregate the convolution vectors. The extensive experiments demonstrate the benefits of the dependency-based convolutional neural networks and the entity mention-based pooling method for event detection. We achieve the state-of-the-art performance on widely used datasets with both perfect and predicted entity mentions.

Original languageEnglish (US)
Title of host publication32nd AAAI Conference on Artificial Intelligence, AAAI 2018
PublisherAAAI press
Pages5900-5907
Number of pages8
ISBN (Electronic)9781577358008
StatePublished - Jan 1 2018
Event32nd AAAI Conference on Artificial Intelligence, AAAI 2018 - New Orleans, United States
Duration: Feb 2 2018Feb 7 2018

Other

Other32nd AAAI Conference on Artificial Intelligence, AAAI 2018
CountryUnited States
CityNew Orleans
Period2/2/182/7/18

Fingerprint

Neural networks
Syntactics
Convolution
Experiments

ASJC Scopus subject areas

  • Artificial Intelligence

Cite this

Nguyen, T. H., & Grishman, R. (2018). Graph convolutional networks with argument-aware pooling for event detection. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018 (pp. 5900-5907). AAAI press.

Graph convolutional networks with argument-aware pooling for event detection. / Nguyen, Thien Huu; Grishman, Ralph.

32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. p. 5900-5907.

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

Nguyen, TH & Grishman, R 2018, Graph convolutional networks with argument-aware pooling for event detection. in 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, pp. 5900-5907, 32nd AAAI Conference on Artificial Intelligence, AAAI 2018, New Orleans, United States, 2/2/18.
Nguyen TH, Grishman R. Graph convolutional networks with argument-aware pooling for event detection. In 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press. 2018. p. 5900-5907
Nguyen, Thien Huu ; Grishman, Ralph. / Graph convolutional networks with argument-aware pooling for event detection. 32nd AAAI Conference on Artificial Intelligence, AAAI 2018. AAAI press, 2018. pp. 5900-5907
@inproceedings{894913d869de45978f87ed43cec56079,
title = "Graph convolutional networks with argument-aware pooling for event detection",
abstract = "The current neural network models for event detection have only considered the sequential representation of sentences. Syntactic representations have not been explored in this area although they provide an effective mechanism to directly link words to their informative context for event detection in the sentences. In this work, we investigate a convolutional neural network based on dependency trees to perform event detection. We propose a novel pooling method that relies on entity mentions to aggregate the convolution vectors. The extensive experiments demonstrate the benefits of the dependency-based convolutional neural networks and the entity mention-based pooling method for event detection. We achieve the state-of-the-art performance on widely used datasets with both perfect and predicted entity mentions.",
author = "Nguyen, {Thien Huu} and Ralph Grishman",
year = "2018",
month = "1",
day = "1",
language = "English (US)",
pages = "5900--5907",
booktitle = "32nd AAAI Conference on Artificial Intelligence, AAAI 2018",
publisher = "AAAI press",

}

TY - GEN

T1 - Graph convolutional networks with argument-aware pooling for event detection

AU - Nguyen, Thien Huu

AU - Grishman, Ralph

PY - 2018/1/1

Y1 - 2018/1/1

N2 - The current neural network models for event detection have only considered the sequential representation of sentences. Syntactic representations have not been explored in this area although they provide an effective mechanism to directly link words to their informative context for event detection in the sentences. In this work, we investigate a convolutional neural network based on dependency trees to perform event detection. We propose a novel pooling method that relies on entity mentions to aggregate the convolution vectors. The extensive experiments demonstrate the benefits of the dependency-based convolutional neural networks and the entity mention-based pooling method for event detection. We achieve the state-of-the-art performance on widely used datasets with both perfect and predicted entity mentions.

AB - The current neural network models for event detection have only considered the sequential representation of sentences. Syntactic representations have not been explored in this area although they provide an effective mechanism to directly link words to their informative context for event detection in the sentences. In this work, we investigate a convolutional neural network based on dependency trees to perform event detection. We propose a novel pooling method that relies on entity mentions to aggregate the convolution vectors. The extensive experiments demonstrate the benefits of the dependency-based convolutional neural networks and the entity mention-based pooling method for event detection. We achieve the state-of-the-art performance on widely used datasets with both perfect and predicted entity mentions.

UR - http://www.scopus.com/inward/record.url?scp=85057274576&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85057274576&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85057274576

SP - 5900

EP - 5907

BT - 32nd AAAI Conference on Artificial Intelligence, AAAI 2018

PB - AAAI press

ER -