@inproceedings{zheng-etal-2025-ahve,
title = "{AHVE}-{CNER}: Aligned Hanzi Visual Encoding Enhance {C}hinese Named Entity Recognition with Multi-Information",
author = "Zheng, Xuhui and
Min, Zhiyuan and
Shi, Bin and
Wang, Hao",
editor = "Rambow, Owen and
Wanner, Leo and
Apidianaki, Marianna and
Al-Khalifa, Hend and
Eugenio, Barbara Di and
Schockaert, Steven",
booktitle = "Proceedings of the 31st International Conference on Computational Linguistics",
month = jan,
year = "2025",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.coling-main.228/",
pages = "3391--3400",
abstract = "The integration of multi-modal information, especially the graphic features of Hanzi, is crucial for improving the performance of Chinese Named Entity Recognition (NER) tasks. However, existing glyph-based models frequently neglect the relationship between pictorial elements and radicals. This paper presents AHVE-CNER, a model that integrates multi-source visual and phonetic information of Hanzi, while explicitly aligning pictographic features with their corresponding radicals. We propose the Gated Pangu-$\pi$ Cross Transformer to effectively facilitate the integration of these multi-modal representations. By leveraging a multi-source glyph alignment strategy, AHVE-CNER demonstrates an improved capability to capture the visual and semantic nuances of Hanzi for NER tasks. Extensive experiments on benchmark datasets validate that AHVE-CNER achieves superior performance compared to existing multi-modal Chinese NER methods. Additional ablation studies further confirm the effectiveness of our visual alignment module and the fusion approach."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zheng-etal-2025-ahve">
<titleInfo>
<title>AHVE-CNER: Aligned Hanzi Visual Encoding Enhance Chinese Named Entity Recognition with Multi-Information</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuhui</namePart>
<namePart type="family">Zheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyuan</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bin</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hao</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-01</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 31st International Conference on Computational Linguistics</title>
</titleInfo>
<name type="personal">
<namePart type="given">Owen</namePart>
<namePart type="family">Rambow</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leo</namePart>
<namePart type="family">Wanner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hend</namePart>
<namePart type="family">Al-Khalifa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Barbara</namePart>
<namePart type="given">Di</namePart>
<namePart type="family">Eugenio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Schockaert</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The integration of multi-modal information, especially the graphic features of Hanzi, is crucial for improving the performance of Chinese Named Entity Recognition (NER) tasks. However, existing glyph-based models frequently neglect the relationship between pictorial elements and radicals. This paper presents AHVE-CNER, a model that integrates multi-source visual and phonetic information of Hanzi, while explicitly aligning pictographic features with their corresponding radicals. We propose the Gated Pangu-π Cross Transformer to effectively facilitate the integration of these multi-modal representations. By leveraging a multi-source glyph alignment strategy, AHVE-CNER demonstrates an improved capability to capture the visual and semantic nuances of Hanzi for NER tasks. Extensive experiments on benchmark datasets validate that AHVE-CNER achieves superior performance compared to existing multi-modal Chinese NER methods. Additional ablation studies further confirm the effectiveness of our visual alignment module and the fusion approach.</abstract>
<identifier type="citekey">zheng-etal-2025-ahve</identifier>
<location>
<url>https://aclanthology.org/2025.coling-main.228/</url>
</location>
<part>
<date>2025-01</date>
<extent unit="page">
<start>3391</start>
<end>3400</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T AHVE-CNER: Aligned Hanzi Visual Encoding Enhance Chinese Named Entity Recognition with Multi-Information
%A Zheng, Xuhui
%A Min, Zhiyuan
%A Shi, Bin
%A Wang, Hao
%Y Rambow, Owen
%Y Wanner, Leo
%Y Apidianaki, Marianna
%Y Al-Khalifa, Hend
%Y Eugenio, Barbara Di
%Y Schockaert, Steven
%S Proceedings of the 31st International Conference on Computational Linguistics
%D 2025
%8 January
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F zheng-etal-2025-ahve
%X The integration of multi-modal information, especially the graphic features of Hanzi, is crucial for improving the performance of Chinese Named Entity Recognition (NER) tasks. However, existing glyph-based models frequently neglect the relationship between pictorial elements and radicals. This paper presents AHVE-CNER, a model that integrates multi-source visual and phonetic information of Hanzi, while explicitly aligning pictographic features with their corresponding radicals. We propose the Gated Pangu-π Cross Transformer to effectively facilitate the integration of these multi-modal representations. By leveraging a multi-source glyph alignment strategy, AHVE-CNER demonstrates an improved capability to capture the visual and semantic nuances of Hanzi for NER tasks. Extensive experiments on benchmark datasets validate that AHVE-CNER achieves superior performance compared to existing multi-modal Chinese NER methods. Additional ablation studies further confirm the effectiveness of our visual alignment module and the fusion approach.
%U https://aclanthology.org/2025.coling-main.228/
%P 3391-3400
Markdown (Informal)
[AHVE-CNER: Aligned Hanzi Visual Encoding Enhance Chinese Named Entity Recognition with Multi-Information](https://aclanthology.org/2025.coling-main.228/) (Zheng et al., COLING 2025)
ACL