@inproceedings{dou-etal-2024-improving-chinese,
title = "Improving {C}hinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling",
author = "Dou, Chenhui and
Gong, Chen and
Li, Zhenghua and
Wang, Zhefeng and
Huai, Baoxing and
Zhang, Min",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.765",
pages = "8732--8742",
abstract = "Nowadays, character-based sequence labeling becomes the mainstream Chinese named entity recognition (CNER) approach, instead of word-based methods, since the latter degrades performance due to propagation of word segmentation (WS) errors. To make use of WS information, previous studies usually learn CNER and WS simultaneously with multi-task learning (MTL) framework, or treat WS information as extra guide features for CNER model, in which the utilization of WS information is indirect and shallow. In light of the complementary information inside multi-grained words, and the close connection between named entities and part-of-speech (POS) tags, this work proposes a tree parsing approach for joint modeling CNER, multi-grained word segmentation (MWS) and POS tagging tasks simultaneously. Specifically, we first propose a unified tree representation for MWS, POS tagging, and CNER.Then, we automatically construct the MWS-POS-NER data based on the unified tree representation for model training. Finally, we present a two-stage joint tree parsing framework. Experimental results on OntoNotes4 and OntoNotes5 show that our proposed approach of jointly modeling CNER with MWS and POS tagging achieves better or comparable performance with latest methods.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="dou-etal-2024-improving-chinese">
<titleInfo>
<title>Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chenhui</namePart>
<namePart type="family">Dou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chen</namePart>
<namePart type="family">Gong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenghua</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhefeng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Baoxing</namePart>
<namePart type="family">Huai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Nowadays, character-based sequence labeling becomes the mainstream Chinese named entity recognition (CNER) approach, instead of word-based methods, since the latter degrades performance due to propagation of word segmentation (WS) errors. To make use of WS information, previous studies usually learn CNER and WS simultaneously with multi-task learning (MTL) framework, or treat WS information as extra guide features for CNER model, in which the utilization of WS information is indirect and shallow. In light of the complementary information inside multi-grained words, and the close connection between named entities and part-of-speech (POS) tags, this work proposes a tree parsing approach for joint modeling CNER, multi-grained word segmentation (MWS) and POS tagging tasks simultaneously. Specifically, we first propose a unified tree representation for MWS, POS tagging, and CNER.Then, we automatically construct the MWS-POS-NER data based on the unified tree representation for model training. Finally, we present a two-stage joint tree parsing framework. Experimental results on OntoNotes4 and OntoNotes5 show that our proposed approach of jointly modeling CNER with MWS and POS tagging achieves better or comparable performance with latest methods.</abstract>
<identifier type="citekey">dou-etal-2024-improving-chinese</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.765</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>8732</start>
<end>8742</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling
%A Dou, Chenhui
%A Gong, Chen
%A Li, Zhenghua
%A Wang, Zhefeng
%A Huai, Baoxing
%A Zhang, Min
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F dou-etal-2024-improving-chinese
%X Nowadays, character-based sequence labeling becomes the mainstream Chinese named entity recognition (CNER) approach, instead of word-based methods, since the latter degrades performance due to propagation of word segmentation (WS) errors. To make use of WS information, previous studies usually learn CNER and WS simultaneously with multi-task learning (MTL) framework, or treat WS information as extra guide features for CNER model, in which the utilization of WS information is indirect and shallow. In light of the complementary information inside multi-grained words, and the close connection between named entities and part-of-speech (POS) tags, this work proposes a tree parsing approach for joint modeling CNER, multi-grained word segmentation (MWS) and POS tagging tasks simultaneously. Specifically, we first propose a unified tree representation for MWS, POS tagging, and CNER.Then, we automatically construct the MWS-POS-NER data based on the unified tree representation for model training. Finally, we present a two-stage joint tree parsing framework. Experimental results on OntoNotes4 and OntoNotes5 show that our proposed approach of jointly modeling CNER with MWS and POS tagging achieves better or comparable performance with latest methods.
%U https://aclanthology.org/2024.lrec-main.765
%P 8732-8742
Markdown (Informal)
[Improving Chinese Named Entity Recognition with Multi-grained Words and Part-of-Speech Tags via Joint Modeling](https://aclanthology.org/2024.lrec-main.765) (Dou et al., LREC-COLING 2024)
ACL