@inproceedings{li-etal-2020-handling,
title = "Handling Rare Entities for Neural Sequence Labeling",
author = "Li, Yangming and
Li, Han and
Yao, Kaisheng and
Li, Xiaolong",
editor = "Jurafsky, Dan and
Chai, Joyce and
Schluter, Natalie and
Tetreault, Joel",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.574/",
doi = "10.18653/v1/2020.acl-main.574",
pages = "6441--6451",
abstract = "One great challenge in neural sequence labeling is the data sparsity problem for rare entity words and phrases. Most of test set entities appear only few times and are even unseen in training corpus, yielding large number of out-of-vocabulary (OOV) and low-frequency (LF) entities during evaluation. In this work, we propose approaches to address this problem. For OOV entities, we introduce local context reconstruction to implicitly incorporate contextual information into their representations. For LF entities, we present delexicalized entity identification to explicitly extract their frequency-agnostic and entity-type-specific representations. Extensive experiments on multiple benchmark datasets show that our model has significantly outperformed all previous methods and achieved new start-of-the-art results. Notably, our methods surpass the model fine-tuned on pre-trained language models without external resource."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2020-handling">
<titleInfo>
<title>Handling Rare Entities for Neural Sequence Labeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yangming</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Han</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kaisheng</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaolong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dan</namePart>
<namePart type="family">Jurafsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joyce</namePart>
<namePart type="family">Chai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Natalie</namePart>
<namePart type="family">Schluter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Tetreault</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>One great challenge in neural sequence labeling is the data sparsity problem for rare entity words and phrases. Most of test set entities appear only few times and are even unseen in training corpus, yielding large number of out-of-vocabulary (OOV) and low-frequency (LF) entities during evaluation. In this work, we propose approaches to address this problem. For OOV entities, we introduce local context reconstruction to implicitly incorporate contextual information into their representations. For LF entities, we present delexicalized entity identification to explicitly extract their frequency-agnostic and entity-type-specific representations. Extensive experiments on multiple benchmark datasets show that our model has significantly outperformed all previous methods and achieved new start-of-the-art results. Notably, our methods surpass the model fine-tuned on pre-trained language models without external resource.</abstract>
<identifier type="citekey">li-etal-2020-handling</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.574</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.574/</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>6441</start>
<end>6451</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Handling Rare Entities for Neural Sequence Labeling
%A Li, Yangming
%A Li, Han
%A Yao, Kaisheng
%A Li, Xiaolong
%Y Jurafsky, Dan
%Y Chai, Joyce
%Y Schluter, Natalie
%Y Tetreault, Joel
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F li-etal-2020-handling
%X One great challenge in neural sequence labeling is the data sparsity problem for rare entity words and phrases. Most of test set entities appear only few times and are even unseen in training corpus, yielding large number of out-of-vocabulary (OOV) and low-frequency (LF) entities during evaluation. In this work, we propose approaches to address this problem. For OOV entities, we introduce local context reconstruction to implicitly incorporate contextual information into their representations. For LF entities, we present delexicalized entity identification to explicitly extract their frequency-agnostic and entity-type-specific representations. Extensive experiments on multiple benchmark datasets show that our model has significantly outperformed all previous methods and achieved new start-of-the-art results. Notably, our methods surpass the model fine-tuned on pre-trained language models without external resource.
%R 10.18653/v1/2020.acl-main.574
%U https://aclanthology.org/2020.acl-main.574/
%U https://doi.org/10.18653/v1/2020.acl-main.574
%P 6441-6451
Markdown (Informal)
[Handling Rare Entities for Neural Sequence Labeling](https://aclanthology.org/2020.acl-main.574/) (Li et al., ACL 2020)
ACL
- Yangming Li, Han Li, Kaisheng Yao, and Xiaolong Li. 2020. Handling Rare Entities for Neural Sequence Labeling. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 6441–6451, Online. Association for Computational Linguistics.