@inproceedings{chen-etal-2022-opdai,
title = "{OPDAI} at {S}em{E}val-2022 Task 11: A hybrid approach for {C}hinese {NER} using outside {W}ikipedia knowledge",
author = "Chen, Ze and
Wang, Kangxu and
Zheng, Jiewen and
Cai, Zijian and
He, Jiarong and
Gao, Jin",
editor = "Emerson, Guy and
Schluter, Natalie and
Stanovsky, Gabriel and
Kumar, Ritesh and
Palmer, Alexis and
Schneider, Nathan and
Singh, Siddharth and
Ratan, Shyam",
booktitle = "Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.semeval-1.204/",
doi = "10.18653/v1/2022.semeval-1.204",
pages = "1488--1493",
abstract = "This article describes the OPDAI submission to SemEval-2022 Task 11 on Chinese complex NER. First, we explore the performance of model-based approaches and their ensemble, finding that fine-tuning the pre-trained Chinese RoBERTa-wwm model with word semantic representation and contextual gazetteer representation performs best among single models. However, the model-based approach performs poorly on test data because of low-context and unseen-entity cases. Then, we extend our system into two stages: (1) generating entity candidates by using neural model, soft-templates and Wikipedia lexicon. (2) predicting the final entity results within a feature-based rank model. For the evaluation, our best submission achieves an $F_1$ score of 0.7954 and attains the third-best score in the Chinese sub-track."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chen-etal-2022-opdai">
<titleInfo>
<title>OPDAI at SemEval-2022 Task 11: A hybrid approach for Chinese NER using outside Wikipedia knowledge</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ze</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kangxu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiewen</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zijian</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiarong</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jin</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guy</namePart>
<namePart type="family">Emerson</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">Gabriel</namePart>
<namePart type="family">Stanovsky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexis</namePart>
<namePart type="family">Palmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathan</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Siddharth</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shyam</namePart>
<namePart type="family">Ratan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This article describes the OPDAI submission to SemEval-2022 Task 11 on Chinese complex NER. First, we explore the performance of model-based approaches and their ensemble, finding that fine-tuning the pre-trained Chinese RoBERTa-wwm model with word semantic representation and contextual gazetteer representation performs best among single models. However, the model-based approach performs poorly on test data because of low-context and unseen-entity cases. Then, we extend our system into two stages: (1) generating entity candidates by using neural model, soft-templates and Wikipedia lexicon. (2) predicting the final entity results within a feature-based rank model. For the evaluation, our best submission achieves an F₁ score of 0.7954 and attains the third-best score in the Chinese sub-track.</abstract>
<identifier type="citekey">chen-etal-2022-opdai</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.204</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.204/</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1488</start>
<end>1493</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T OPDAI at SemEval-2022 Task 11: A hybrid approach for Chinese NER using outside Wikipedia knowledge
%A Chen, Ze
%A Wang, Kangxu
%A Zheng, Jiewen
%A Cai, Zijian
%A He, Jiarong
%A Gao, Jin
%Y Emerson, Guy
%Y Schluter, Natalie
%Y Stanovsky, Gabriel
%Y Kumar, Ritesh
%Y Palmer, Alexis
%Y Schneider, Nathan
%Y Singh, Siddharth
%Y Ratan, Shyam
%S Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022)
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F chen-etal-2022-opdai
%X This article describes the OPDAI submission to SemEval-2022 Task 11 on Chinese complex NER. First, we explore the performance of model-based approaches and their ensemble, finding that fine-tuning the pre-trained Chinese RoBERTa-wwm model with word semantic representation and contextual gazetteer representation performs best among single models. However, the model-based approach performs poorly on test data because of low-context and unseen-entity cases. Then, we extend our system into two stages: (1) generating entity candidates by using neural model, soft-templates and Wikipedia lexicon. (2) predicting the final entity results within a feature-based rank model. For the evaluation, our best submission achieves an F₁ score of 0.7954 and attains the third-best score in the Chinese sub-track.
%R 10.18653/v1/2022.semeval-1.204
%U https://aclanthology.org/2022.semeval-1.204/
%U https://doi.org/10.18653/v1/2022.semeval-1.204
%P 1488-1493
Markdown (Informal)
[OPDAI at SemEval-2022 Task 11: A hybrid approach for Chinese NER using outside Wikipedia knowledge](https://aclanthology.org/2022.semeval-1.204/) (Chen et al., SemEval 2022)
ACL