@inproceedings{chen-etal-2020-reconstructing,
title = "Reconstructing Event Regions for Event Extraction via Graph Attention Networks",
author = "Chen, Pei and
Yang, Hang and
Liu, Kang and
Huang, Ruihong and
Chen, Yubo and
Wang, Taifeng and
Zhao, Jun",
booktitle = "Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing",
month = dec,
year = "2020",
address = "Suzhou, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.aacl-main.81",
pages = "811--820",
abstract = "Event information is usually scattered across multiple sentences within a document. The local sentence-level event extractors often yield many noisy event role filler extractions in the absence of a broader view of the document-level context. Filtering spurious extractions and aggregating event information in a document remains a challenging problem. Following the observation that a document has several relevant event regions densely populated with event role fillers, we build graphs with candidate role filler extractions enriched by sentential embeddings as nodes, and use graph attention networks to identify event regions in a document and aggregate event information. We characterize edges between candidate extractions in a graph into rich vector representations to facilitate event region identification. The experimental results on two datasets of two languages show that our approach yields new state-of-the-art performance for the challenging event extraction task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2020-reconstructing">
<titleInfo>
<title>Reconstructing Event Regions for Event Extraction via Graph Attention Networks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hang</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruihong</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Taifeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-dec</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Suzhou, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Event information is usually scattered across multiple sentences within a document. The local sentence-level event extractors often yield many noisy event role filler extractions in the absence of a broader view of the document-level context. Filtering spurious extractions and aggregating event information in a document remains a challenging problem. Following the observation that a document has several relevant event regions densely populated with event role fillers, we build graphs with candidate role filler extractions enriched by sentential embeddings as nodes, and use graph attention networks to identify event regions in a document and aggregate event information. We characterize edges between candidate extractions in a graph into rich vector representations to facilitate event region identification. The experimental results on two datasets of two languages show that our approach yields new state-of-the-art performance for the challenging event extraction task.</abstract>
<identifier type="citekey">chen-etal-2020-reconstructing</identifier>
<location>
<url>https://aclanthology.org/2020.aacl-main.81</url>
</location>
<part>
<date>2020-dec</date>
<extent unit="page">
<start>811</start>
<end>820</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Reconstructing Event Regions for Event Extraction via Graph Attention Networks
%A Chen, Pei
%A Yang, Hang
%A Liu, Kang
%A Huang, Ruihong
%A Chen, Yubo
%A Wang, Taifeng
%A Zhao, Jun
%S Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing
%D 2020
%8 dec
%I Association for Computational Linguistics
%C Suzhou, China
%F chen-etal-2020-reconstructing
%X Event information is usually scattered across multiple sentences within a document. The local sentence-level event extractors often yield many noisy event role filler extractions in the absence of a broader view of the document-level context. Filtering spurious extractions and aggregating event information in a document remains a challenging problem. Following the observation that a document has several relevant event regions densely populated with event role fillers, we build graphs with candidate role filler extractions enriched by sentential embeddings as nodes, and use graph attention networks to identify event regions in a document and aggregate event information. We characterize edges between candidate extractions in a graph into rich vector representations to facilitate event region identification. The experimental results on two datasets of two languages show that our approach yields new state-of-the-art performance for the challenging event extraction task.
%U https://aclanthology.org/2020.aacl-main.81
%P 811-820
Markdown (Informal)
[Reconstructing Event Regions for Event Extraction via Graph Attention Networks](https://aclanthology.org/2020.aacl-main.81) (Chen et al., AACL 2020)
ACL
- Pei Chen, Hang Yang, Kang Liu, Ruihong Huang, Yubo Chen, Taifeng Wang, and Jun Zhao. 2020. Reconstructing Event Regions for Event Extraction via Graph Attention Networks. In Proceedings of the 1st Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics and the 10th International Joint Conference on Natural Language Processing, pages 811–820, Suzhou, China. Association for Computational Linguistics.