@inproceedings{han-etal-2022-cross,
title = "Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages",
author = "Han, Xu and
Luo, Yuqi and
Chen, Weize and
Liu, Zhiyuan and
Sun, Maosong and
Botong, Zhou and
Fei, Hao and
Zheng, Suncong",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.159",
doi = "10.18653/v1/2022.acl-long.159",
pages = "2241--2250",
abstract = "Fine-grained entity typing (FGET) aims to classify named entity mentions into fine-grained entity types, which is meaningful for entity-related NLP tasks. For FGET, a key challenge is the low-resource problem {---} the complex entity type hierarchy makes it difficult to manually label data. Especially for those languages other than English, human-labeled data is extremely scarce. In this paper, we propose a cross-lingual contrastive learning framework to learn FGET models for low-resource languages. Specifically, we use multi-lingual pre-trained language models (PLMs) as the backbone to transfer the typing knowledge from high-resource languages (such as English) to low-resource languages (such as Chinese). Furthermore, we introduce entity-pair-oriented heuristic rules as well as machine translation to obtain cross-lingual distantly-supervised data, and apply cross-lingual contrastive learning on the distantly-supervised data to enhance the backbone PLMs. Experimental results show that by applying our framework, we can easily learn effective FGET models for low-resource languages, even without any language-specific human-labeled data. Our code is also available at \url{https://github.com/thunlp/CrossET}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2022-cross">
<titleInfo>
<title>Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xu</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuqi</namePart>
<namePart type="family">Luo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weize</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Maosong</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Botong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Fei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Suncong</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Fine-grained entity typing (FGET) aims to classify named entity mentions into fine-grained entity types, which is meaningful for entity-related NLP tasks. For FGET, a key challenge is the low-resource problem — the complex entity type hierarchy makes it difficult to manually label data. Especially for those languages other than English, human-labeled data is extremely scarce. In this paper, we propose a cross-lingual contrastive learning framework to learn FGET models for low-resource languages. Specifically, we use multi-lingual pre-trained language models (PLMs) as the backbone to transfer the typing knowledge from high-resource languages (such as English) to low-resource languages (such as Chinese). Furthermore, we introduce entity-pair-oriented heuristic rules as well as machine translation to obtain cross-lingual distantly-supervised data, and apply cross-lingual contrastive learning on the distantly-supervised data to enhance the backbone PLMs. Experimental results show that by applying our framework, we can easily learn effective FGET models for low-resource languages, even without any language-specific human-labeled data. Our code is also available at https://github.com/thunlp/CrossET.</abstract>
<identifier type="citekey">han-etal-2022-cross</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.159</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.159</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>2241</start>
<end>2250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages
%A Han, Xu
%A Luo, Yuqi
%A Chen, Weize
%A Liu, Zhiyuan
%A Sun, Maosong
%A Botong, Zhou
%A Fei, Hao
%A Zheng, Suncong
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F han-etal-2022-cross
%X Fine-grained entity typing (FGET) aims to classify named entity mentions into fine-grained entity types, which is meaningful for entity-related NLP tasks. For FGET, a key challenge is the low-resource problem — the complex entity type hierarchy makes it difficult to manually label data. Especially for those languages other than English, human-labeled data is extremely scarce. In this paper, we propose a cross-lingual contrastive learning framework to learn FGET models for low-resource languages. Specifically, we use multi-lingual pre-trained language models (PLMs) as the backbone to transfer the typing knowledge from high-resource languages (such as English) to low-resource languages (such as Chinese). Furthermore, we introduce entity-pair-oriented heuristic rules as well as machine translation to obtain cross-lingual distantly-supervised data, and apply cross-lingual contrastive learning on the distantly-supervised data to enhance the backbone PLMs. Experimental results show that by applying our framework, we can easily learn effective FGET models for low-resource languages, even without any language-specific human-labeled data. Our code is also available at https://github.com/thunlp/CrossET.
%R 10.18653/v1/2022.acl-long.159
%U https://aclanthology.org/2022.acl-long.159
%U https://doi.org/10.18653/v1/2022.acl-long.159
%P 2241-2250
Markdown (Informal)
[Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages](https://aclanthology.org/2022.acl-long.159) (Han et al., ACL 2022)
ACL
- Xu Han, Yuqi Luo, Weize Chen, Zhiyuan Liu, Maosong Sun, Zhou Botong, Hao Fei, and Suncong Zheng. 2022. Cross-Lingual Contrastive Learning for Fine-Grained Entity Typing for Low-Resource Languages. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 2241–2250, Dublin, Ireland. Association for Computational Linguistics.