@inproceedings{wang-etal-2021-unire,
title = "{U}ni{RE}: A Unified Label Space for Entity Relation Extraction",
author = "Wang, Yijun and
Sun, Changzhi and
Wu, Yuanbin and
Zhou, Hao and
Li, Lei and
Yan, Junchi",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.19",
doi = "10.18653/v1/2021.acl-long.19",
pages = "220--231",
abstract = "Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks{'} label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell{'}s label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wang-etal-2021-unire">
<titleInfo>
<title>UniRE: A Unified Label Space for Entity Relation Extraction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yijun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Changzhi</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuanbin</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lei</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junchi</namePart>
<namePart type="family">Yan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks’ label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell’s label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.</abstract>
<identifier type="citekey">wang-etal-2021-unire</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.19</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.19</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>220</start>
<end>231</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T UniRE: A Unified Label Space for Entity Relation Extraction
%A Wang, Yijun
%A Sun, Changzhi
%A Wu, Yuanbin
%A Zhou, Hao
%A Li, Lei
%A Yan, Junchi
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F wang-etal-2021-unire
%X Many joint entity relation extraction models setup two separated label spaces for the two sub-tasks (i.e., entity detection and relation classification). We argue that this setting may hinder the information interaction between entities and relations. In this work, we propose to eliminate the different treatment on the two sub-tasks’ label spaces. The input of our model is a table containing all word pairs from a sentence. Entities and relations are represented by squares and rectangles in the table. We apply a unified classifier to predict each cell’s label, which unifies the learning of two sub-tasks. For testing, an effective (yet fast) approximate decoder is proposed for finding squares and rectangles from tables. Experiments on three benchmarks (ACE04, ACE05, SciERC) show that, using only half the number of parameters, our model achieves competitive accuracy with the best extractor, and is faster.
%R 10.18653/v1/2021.acl-long.19
%U https://aclanthology.org/2021.acl-long.19
%U https://doi.org/10.18653/v1/2021.acl-long.19
%P 220-231
Markdown (Informal)
[UniRE: A Unified Label Space for Entity Relation Extraction](https://aclanthology.org/2021.acl-long.19) (Wang et al., ACL-IJCNLP 2021)
ACL
- Yijun Wang, Changzhi Sun, Yuanbin Wu, Hao Zhou, Lei Li, and Junchi Yan. 2021. UniRE: A Unified Label Space for Entity Relation Extraction. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 220–231, Online. Association for Computational Linguistics.