@inproceedings{xiong-etal-2022-multi,
title = "A Multi-Gate Encoder for Joint Entity and Relation Extraction",
author = "Xiong, Xiong and
Yunfei, Liu and
Anqi, Liu and
Shuai, Gong and
Shengyang, Li",
booktitle = "Proceedings of the 21st Chinese National Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Nanchang, China",
publisher = "Chinese Information Processing Society of China",
url = "https://aclanthology.org/2022.ccl-1.75",
pages = "848--860",
abstract = "{``}Named entity recognition and relation extraction are core sub-tasks of relational triple extraction. Recent studies have used parameter sharing or joint decoding to create interaction between these two tasks. However, ensuring the specificity of task-specific traits while the two tasks interact properly is a huge difficulty. We propose a multi-gate encoder that models bidirectional task interaction while keeping sufficient feature specificity based on gating mechanism in this paper. Precisely, we design two types of independent gates: task gates to generate task-specific features and interaction gates to generate instructive features to guide the opposite task. Our experiments show that our method increases the state-of-the-art (SOTA) relation F1 scores on ACE04, ACE05 and SciERC datasets to 63.8{\%} (+1.3{\%}), 68.2{\%} (+1.4{\%}), 39.4{\%} (+1.0{\%}), respectively, with higher inference speed over previous SOTA model.{''}",
language = "English",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="xiong-etal-2022-multi">
<titleInfo>
<title>A Multi-Gate Encoder for Joint Entity and Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiong</namePart>
<namePart type="family">Xiong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Yunfei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Liu</namePart>
<namePart type="family">Anqi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gong</namePart>
<namePart type="family">Shuai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Li</namePart>
<namePart type="family">Shengyang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<language>
<languageTerm type="text">English</languageTerm>
<languageTerm type="code" authority="iso639-2b">eng</languageTerm>
</language>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Chinese National Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Chinese Information Processing Society of China</publisher>
<place>
<placeTerm type="text">Nanchang, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>“Named entity recognition and relation extraction are core sub-tasks of relational triple extraction. Recent studies have used parameter sharing or joint decoding to create interaction between these two tasks. However, ensuring the specificity of task-specific traits while the two tasks interact properly is a huge difficulty. We propose a multi-gate encoder that models bidirectional task interaction while keeping sufficient feature specificity based on gating mechanism in this paper. Precisely, we design two types of independent gates: task gates to generate task-specific features and interaction gates to generate instructive features to guide the opposite task. Our experiments show that our method increases the state-of-the-art (SOTA) relation F1 scores on ACE04, ACE05 and SciERC datasets to 63.8% (+1.3%), 68.2% (+1.4%), 39.4% (+1.0%), respectively, with higher inference speed over previous SOTA model.”</abstract>
<identifier type="citekey">xiong-etal-2022-multi</identifier>
<location>
<url>https://aclanthology.org/2022.ccl-1.75</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>848</start>
<end>860</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Multi-Gate Encoder for Joint Entity and Relation Extraction
%A Xiong, Xiong
%A Yunfei, Liu
%A Anqi, Liu
%A Shuai, Gong
%A Shengyang, Li
%S Proceedings of the 21st Chinese National Conference on Computational Linguistics
%D 2022
%8 October
%I Chinese Information Processing Society of China
%C Nanchang, China
%G English
%F xiong-etal-2022-multi
%X “Named entity recognition and relation extraction are core sub-tasks of relational triple extraction. Recent studies have used parameter sharing or joint decoding to create interaction between these two tasks. However, ensuring the specificity of task-specific traits while the two tasks interact properly is a huge difficulty. We propose a multi-gate encoder that models bidirectional task interaction while keeping sufficient feature specificity based on gating mechanism in this paper. Precisely, we design two types of independent gates: task gates to generate task-specific features and interaction gates to generate instructive features to guide the opposite task. Our experiments show that our method increases the state-of-the-art (SOTA) relation F1 scores on ACE04, ACE05 and SciERC datasets to 63.8% (+1.3%), 68.2% (+1.4%), 39.4% (+1.0%), respectively, with higher inference speed over previous SOTA model.”
%U https://aclanthology.org/2022.ccl-1.75
%P 848-860
Markdown (Informal)
[A Multi-Gate Encoder for Joint Entity and Relation Extraction](https://aclanthology.org/2022.ccl-1.75) (Xiong et al., CCL 2022)
ACL