@inproceedings{bao-etal-2024-employing,
title = "Employing Glyphic Information for {C}hinese Event Extraction with Vision-Language Model",
author = "Bao, Xiaoyi and
Gu, Jinghang and
Wang, Zhongqing and
Qiang, Minjie and
Huang, Chu-Ren",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.58/",
doi = "10.18653/v1/2024.findings-emnlp.58",
pages = "1068--1080",
abstract = "As a complex task that requires rich information input, features from various aspects have been utilized in event extraction. However, most of the previous works ignored the value of glyph, which could contain enriched semantic information and can not be fully expressed by the pre-trained embedding in hieroglyphic languages like Chinese. We argue that, compared with combining the sophisticated textual features, glyphic information from visual modality could provide us with extra and straight semantic information in extracting events. Motivated by this, we propose a glyphic multi-modal Chinese event extraction model with hieroglyphic images to capture the intra- and inter-character morphological structure from the sequence. Extensive experiments build a new state-of-the-art performance in the ACE2005 Chinese and KBP Eval 2017 dataset, which underscores the effectiveness of our proposed glyphic event extraction model, and more importantly, the glyphic feature can be obtained at nearly zero cost."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bao-etal-2024-employing">
<titleInfo>
<title>Employing Glyphic Information for Chinese Event Extraction with Vision-Language Model</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiaoyi</namePart>
<namePart type="family">Bao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghang</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhongqing</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minjie</namePart>
<namePart type="family">Qiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chu-Ren</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yaser</namePart>
<namePart type="family">Al-Onaizan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yun-Nung</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Miami, Florida, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As a complex task that requires rich information input, features from various aspects have been utilized in event extraction. However, most of the previous works ignored the value of glyph, which could contain enriched semantic information and can not be fully expressed by the pre-trained embedding in hieroglyphic languages like Chinese. We argue that, compared with combining the sophisticated textual features, glyphic information from visual modality could provide us with extra and straight semantic information in extracting events. Motivated by this, we propose a glyphic multi-modal Chinese event extraction model with hieroglyphic images to capture the intra- and inter-character morphological structure from the sequence. Extensive experiments build a new state-of-the-art performance in the ACE2005 Chinese and KBP Eval 2017 dataset, which underscores the effectiveness of our proposed glyphic event extraction model, and more importantly, the glyphic feature can be obtained at nearly zero cost.</abstract>
<identifier type="citekey">bao-etal-2024-employing</identifier>
<identifier type="doi">10.18653/v1/2024.findings-emnlp.58</identifier>
<location>
<url>https://aclanthology.org/2024.findings-emnlp.58/</url>
</location>
<part>
<date>2024-11</date>
<extent unit="page">
<start>1068</start>
<end>1080</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Employing Glyphic Information for Chinese Event Extraction with Vision-Language Model
%A Bao, Xiaoyi
%A Gu, Jinghang
%A Wang, Zhongqing
%A Qiang, Minjie
%A Huang, Chu-Ren
%Y Al-Onaizan, Yaser
%Y Bansal, Mohit
%Y Chen, Yun-Nung
%S Findings of the Association for Computational Linguistics: EMNLP 2024
%D 2024
%8 November
%I Association for Computational Linguistics
%C Miami, Florida, USA
%F bao-etal-2024-employing
%X As a complex task that requires rich information input, features from various aspects have been utilized in event extraction. However, most of the previous works ignored the value of glyph, which could contain enriched semantic information and can not be fully expressed by the pre-trained embedding in hieroglyphic languages like Chinese. We argue that, compared with combining the sophisticated textual features, glyphic information from visual modality could provide us with extra and straight semantic information in extracting events. Motivated by this, we propose a glyphic multi-modal Chinese event extraction model with hieroglyphic images to capture the intra- and inter-character morphological structure from the sequence. Extensive experiments build a new state-of-the-art performance in the ACE2005 Chinese and KBP Eval 2017 dataset, which underscores the effectiveness of our proposed glyphic event extraction model, and more importantly, the glyphic feature can be obtained at nearly zero cost.
%R 10.18653/v1/2024.findings-emnlp.58
%U https://aclanthology.org/2024.findings-emnlp.58/
%U https://doi.org/10.18653/v1/2024.findings-emnlp.58
%P 1068-1080
Markdown (Informal)
[Employing Glyphic Information for Chinese Event Extraction with Vision-Language Model](https://aclanthology.org/2024.findings-emnlp.58/) (Bao et al., Findings 2024)
ACL