@inproceedings{ma-etal-2023-ustc,
title = "{USTC}-{NELSLIP} at {S}em{E}val-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex {NER}",
author = "Ma, Jun-Yu and
Gu, Jia-Chen and
Qi, Jiajun and
Ling, Zhenhua and
Liu, Quan and
Zhao, Xiaoyi",
editor = {Ojha, Atul Kr. and
Do{\u{g}}ru{\"o}z, A. Seza and
Da San Martino, Giovanni and
Tayyar Madabushi, Harish and
Kumar, Ritesh and
Sartori, Elisa},
booktitle = "Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.semeval-1.89",
doi = "10.18653/v1/2023.semeval-1.89",
pages = "651--659",
abstract = "This paper describes the system developed by the USTC-NELSLIP team for SemEval-2023 Task 2 Multilingual Complex Named Entity Recognition (MultiCoNER II). We propose a method named Statistical Construction and Dual Adaptation of Gazetteer (SCDAG) for Multilingual Complex NER. The method first utilizes a statistics-based approach to construct a gazetteer. Secondly, the representations of gazetteer networks and language models are adapted by minimizing the KL divergence between them at the sentence-level and entity-level. Finally, these two networks are then integrated for supervised named entity recognition (NER) training. The proposed method is applied to several state-of-the-art Transformer-based NER models with a gazetteer built from Wikidata, and shows great generalization ability across them. The final predictions are derived from an ensemble of these trained models. Experimental results and detailed analysis verify the effectiveness of the proposed method. The official results show that our system ranked 1st on one track (Hindi) in this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ma-etal-2023-ustc">
<titleInfo>
<title>USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jun-Yu</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jia-Chen</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Qi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhua</namePart>
<namePart type="family">Ling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quan</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaoyi</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">A</namePart>
<namePart type="given">Seza</namePart>
<namePart type="family">Doğruöz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Giovanni</namePart>
<namePart type="family">Da San Martino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harish</namePart>
<namePart type="family">Tayyar Madabushi</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">Elisa</namePart>
<namePart type="family">Sartori</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper describes the system developed by the USTC-NELSLIP team for SemEval-2023 Task 2 Multilingual Complex Named Entity Recognition (MultiCoNER II). We propose a method named Statistical Construction and Dual Adaptation of Gazetteer (SCDAG) for Multilingual Complex NER. The method first utilizes a statistics-based approach to construct a gazetteer. Secondly, the representations of gazetteer networks and language models are adapted by minimizing the KL divergence between them at the sentence-level and entity-level. Finally, these two networks are then integrated for supervised named entity recognition (NER) training. The proposed method is applied to several state-of-the-art Transformer-based NER models with a gazetteer built from Wikidata, and shows great generalization ability across them. The final predictions are derived from an ensemble of these trained models. Experimental results and detailed analysis verify the effectiveness of the proposed method. The official results show that our system ranked 1st on one track (Hindi) in this task.</abstract>
<identifier type="citekey">ma-etal-2023-ustc</identifier>
<identifier type="doi">10.18653/v1/2023.semeval-1.89</identifier>
<location>
<url>https://aclanthology.org/2023.semeval-1.89</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>651</start>
<end>659</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER
%A Ma, Jun-Yu
%A Gu, Jia-Chen
%A Qi, Jiajun
%A Ling, Zhenhua
%A Liu, Quan
%A Zhao, Xiaoyi
%Y Ojha, Atul Kr.
%Y Doğruöz, A. Seza
%Y Da San Martino, Giovanni
%Y Tayyar Madabushi, Harish
%Y Kumar, Ritesh
%Y Sartori, Elisa
%S Proceedings of the 17th International Workshop on Semantic Evaluation (SemEval-2023)
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F ma-etal-2023-ustc
%X This paper describes the system developed by the USTC-NELSLIP team for SemEval-2023 Task 2 Multilingual Complex Named Entity Recognition (MultiCoNER II). We propose a method named Statistical Construction and Dual Adaptation of Gazetteer (SCDAG) for Multilingual Complex NER. The method first utilizes a statistics-based approach to construct a gazetteer. Secondly, the representations of gazetteer networks and language models are adapted by minimizing the KL divergence between them at the sentence-level and entity-level. Finally, these two networks are then integrated for supervised named entity recognition (NER) training. The proposed method is applied to several state-of-the-art Transformer-based NER models with a gazetteer built from Wikidata, and shows great generalization ability across them. The final predictions are derived from an ensemble of these trained models. Experimental results and detailed analysis verify the effectiveness of the proposed method. The official results show that our system ranked 1st on one track (Hindi) in this task.
%R 10.18653/v1/2023.semeval-1.89
%U https://aclanthology.org/2023.semeval-1.89
%U https://doi.org/10.18653/v1/2023.semeval-1.89
%P 651-659
Markdown (Informal)
[USTC-NELSLIP at SemEval-2023 Task 2: Statistical Construction and Dual Adaptation of Gazetteer for Multilingual Complex NER](https://aclanthology.org/2023.semeval-1.89) (Ma et al., SemEval 2023)
ACL