@inproceedings{fu-etal-2022-casia,
title = "{CASIA} at {S}em{E}val-2022 Task 11: {C}hinese Named Entity Recognition for Complex and Ambiguous Entities",
author = "Fu, Jia and
Gan, Zhen and
Li, Zhucong and
Li, Sirui and
Sui, Dianbo and
Chen, Yubo and
Liu, Kang and
Zhao, Jun",
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-1.208",
doi = "10.18653/v1/2022.semeval-1.208",
pages = "1518--1523",
abstract = "This paper describes our approach to develop a complex named entity recognition system in SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition,Track 9 - Chinese. In this task, we need to identify the entity boundaries and categorylabels for the six identified categories of CW,LOC, PER, GRP, CORP, and PORD.The task focuses on detecting semantically ambiguous and complex entities in short and low-context settings. We constructed a hybrid system based on Roberta-large model with three training mechanisms and a series of data gugmentation.Three training mechanisms include adversarial training, Child-Tuning training, and continued pre-training. The core idea of the hybrid system is to improve the performance of the model in complex environments by introducing more domain knowledge through data augmentation and continuing pre-training domain adaptation of the model. Our proposed method in this paper achieves a macro-F1 of 0.797 on the final test set, ranking second.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fu-etal-2022-casia">
<titleInfo>
<title>CASIA at SemEval-2022 Task 11: Chinese Named Entity Recognition for Complex and Ambiguous Entities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jia</namePart>
<namePart type="family">Fu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhen</namePart>
<namePart type="family">Gan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhucong</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sirui</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dianbo</namePart>
<namePart type="family">Sui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yubo</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Zhao</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 paper describes our approach to develop a complex named entity recognition system in SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition,Track 9 - Chinese. In this task, we need to identify the entity boundaries and categorylabels for the six identified categories of CW,LOC, PER, GRP, CORP, and PORD.The task focuses on detecting semantically ambiguous and complex entities in short and low-context settings. We constructed a hybrid system based on Roberta-large model with three training mechanisms and a series of data gugmentation.Three training mechanisms include adversarial training, Child-Tuning training, and continued pre-training. The core idea of the hybrid system is to improve the performance of the model in complex environments by introducing more domain knowledge through data augmentation and continuing pre-training domain adaptation of the model. Our proposed method in this paper achieves a macro-F1 of 0.797 on the final test set, ranking second.</abstract>
<identifier type="citekey">fu-etal-2022-casia</identifier>
<identifier type="doi">10.18653/v1/2022.semeval-1.208</identifier>
<location>
<url>https://aclanthology.org/2022.semeval-1.208</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1518</start>
<end>1523</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CASIA at SemEval-2022 Task 11: Chinese Named Entity Recognition for Complex and Ambiguous Entities
%A Fu, Jia
%A Gan, Zhen
%A Li, Zhucong
%A Li, Sirui
%A Sui, Dianbo
%A Chen, Yubo
%A Liu, Kang
%A Zhao, Jun
%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 fu-etal-2022-casia
%X This paper describes our approach to develop a complex named entity recognition system in SemEval 2022 Task 11: MultiCoNER Multilingual Complex Named Entity Recognition,Track 9 - Chinese. In this task, we need to identify the entity boundaries and categorylabels for the six identified categories of CW,LOC, PER, GRP, CORP, and PORD.The task focuses on detecting semantically ambiguous and complex entities in short and low-context settings. We constructed a hybrid system based on Roberta-large model with three training mechanisms and a series of data gugmentation.Three training mechanisms include adversarial training, Child-Tuning training, and continued pre-training. The core idea of the hybrid system is to improve the performance of the model in complex environments by introducing more domain knowledge through data augmentation and continuing pre-training domain adaptation of the model. Our proposed method in this paper achieves a macro-F1 of 0.797 on the final test set, ranking second.
%R 10.18653/v1/2022.semeval-1.208
%U https://aclanthology.org/2022.semeval-1.208
%U https://doi.org/10.18653/v1/2022.semeval-1.208
%P 1518-1523
Markdown (Informal)
[CASIA at SemEval-2022 Task 11: Chinese Named Entity Recognition for Complex and Ambiguous Entities](https://aclanthology.org/2022.semeval-1.208) (Fu et al., SemEval 2022)
ACL
- Jia Fu, Zhen Gan, Zhucong Li, Sirui Li, Dianbo Sui, Yubo Chen, Kang Liu, and Jun Zhao. 2022. CASIA at SemEval-2022 Task 11: Chinese Named Entity Recognition for Complex and Ambiguous Entities. In Proceedings of the 16th International Workshop on Semantic Evaluation (SemEval-2022), pages 1518–1523, Seattle, United States. Association for Computational Linguistics.