@inproceedings{si-etal-2022-scl,
title = "{SCL}-{RAI}: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in {NER}",
author = "Si, Shuzheng and
Zeng, Shuang and
Lin, Jiaxing and
Chang, Baobao",
booktitle = "Proceedings of the 29th International Conference on Computational Linguistics",
month = oct,
year = "2022",
address = "Gyeongju, Republic of Korea",
publisher = "International Committee on Computational Linguistics",
url = "https://aclanthology.org/2022.coling-1.202",
pages = "2313--2318",
abstract = "Unlabeled Entity Problem (UEP) in Named Entity Recognition (NER) datasets seriously hinders the improvement of NER performance. This paper proposes SCL-RAI to cope with this problem. Firstly, we decrease the distance of span representations with the same label while increasing it for different ones via span-based contrastive learning, which relieves the ambiguity among entities and improves the robustness of the model over unlabeled entities. Then we propose retrieval augmented inference to mitigate the decision boundary shifting problem. Our method significantly outperforms the previous SOTA method by 4.21{\%} and 8.64{\%} F1-score on two real-world datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="si-etal-2022-scl">
<titleInfo>
<title>SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuzheng</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaxing</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baobao</namePart>
<namePart type="family">Chang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 29th International Conference on Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>International Committee on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Gyeongju, Republic of Korea</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Unlabeled Entity Problem (UEP) in Named Entity Recognition (NER) datasets seriously hinders the improvement of NER performance. This paper proposes SCL-RAI to cope with this problem. Firstly, we decrease the distance of span representations with the same label while increasing it for different ones via span-based contrastive learning, which relieves the ambiguity among entities and improves the robustness of the model over unlabeled entities. Then we propose retrieval augmented inference to mitigate the decision boundary shifting problem. Our method significantly outperforms the previous SOTA method by 4.21% and 8.64% F1-score on two real-world datasets.</abstract>
<identifier type="citekey">si-etal-2022-scl</identifier>
<location>
<url>https://aclanthology.org/2022.coling-1.202</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>2313</start>
<end>2318</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER
%A Si, Shuzheng
%A Zeng, Shuang
%A Lin, Jiaxing
%A Chang, Baobao
%S Proceedings of the 29th International Conference on Computational Linguistics
%D 2022
%8 October
%I International Committee on Computational Linguistics
%C Gyeongju, Republic of Korea
%F si-etal-2022-scl
%X Unlabeled Entity Problem (UEP) in Named Entity Recognition (NER) datasets seriously hinders the improvement of NER performance. This paper proposes SCL-RAI to cope with this problem. Firstly, we decrease the distance of span representations with the same label while increasing it for different ones via span-based contrastive learning, which relieves the ambiguity among entities and improves the robustness of the model over unlabeled entities. Then we propose retrieval augmented inference to mitigate the decision boundary shifting problem. Our method significantly outperforms the previous SOTA method by 4.21% and 8.64% F1-score on two real-world datasets.
%U https://aclanthology.org/2022.coling-1.202
%P 2313-2318
Markdown (Informal)
[SCL-RAI: Span-based Contrastive Learning with Retrieval Augmented Inference for Unlabeled Entity Problem in NER](https://aclanthology.org/2022.coling-1.202) (Si et al., COLING 2022)
ACL