@inproceedings{lin-etal-2024-kpatch-knowledge,
title = "{KP}atch: Knowledge Patch to Pre-trained Language Model for Zero-Shot Stance Detection on Social Media",
author = "Lin, Shuohao and
Chen, Wei and
Gao, Yunpeng and
Jiang, Zhishu and
Liao, Mengqi and
Zhang, Zhiyu and
Zhao, Shuyuan and
Wan, Huaiyu",
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.871",
pages = "9961--9973",
abstract = "Zero-shot stance detection on social media (ZSSD-SM) aims to distinguish the attitude in tweets towards an unseen target. Previous work capture latent variables between source and target domains to perform this task, but the lack of context knowledge hinders the detection performance. Recent studies have been devoted to obtaining the accurate representation of tweets by bringing additional facts from Knowledge Graph (KG), showing promising performance. However, these knowledge injection methods still suffer from two challenges: (i) The pipeline of knowledge injection causes error accumulation and (ii) irrelevant knowledge makes them fail to understand the semantics. In this paper, we propose a novel knowledge injection method for ZSSD-SM, which adopts two training stages, namely knowledge compression and task guidance, to flexibly inject knowledge into the pre-trained language model (PLM) and adaptively expand tweets context. Specifically, in the knowledge compression stage, the latent representation of KG is reconstructed by the triplet denoising task and compressed into external matrices; while in the task guidance stage, the frozen matrices are employed to guide the PLM to adaptively extract its own context-related knowledge, and then complete the fine-tuning of the ZSSD-SM task. Extensive experiments on multiple datasets show the effectiveness of our proposed method. The code is available at: https://github.com/ShuohaoLin/KPatch.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lin-etal-2024-kpatch-knowledge">
<titleInfo>
<title>KPatch: Knowledge Patch to Pre-trained Language Model for Zero-Shot Stance Detection on Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shuohao</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunpeng</namePart>
<namePart type="family">Gao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhishu</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengqi</namePart>
<namePart type="family">Liao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuyuan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huaiyu</namePart>
<namePart type="family">Wan</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>Zero-shot stance detection on social media (ZSSD-SM) aims to distinguish the attitude in tweets towards an unseen target. Previous work capture latent variables between source and target domains to perform this task, but the lack of context knowledge hinders the detection performance. Recent studies have been devoted to obtaining the accurate representation of tweets by bringing additional facts from Knowledge Graph (KG), showing promising performance. However, these knowledge injection methods still suffer from two challenges: (i) The pipeline of knowledge injection causes error accumulation and (ii) irrelevant knowledge makes them fail to understand the semantics. In this paper, we propose a novel knowledge injection method for ZSSD-SM, which adopts two training stages, namely knowledge compression and task guidance, to flexibly inject knowledge into the pre-trained language model (PLM) and adaptively expand tweets context. Specifically, in the knowledge compression stage, the latent representation of KG is reconstructed by the triplet denoising task and compressed into external matrices; while in the task guidance stage, the frozen matrices are employed to guide the PLM to adaptively extract its own context-related knowledge, and then complete the fine-tuning of the ZSSD-SM task. Extensive experiments on multiple datasets show the effectiveness of our proposed method. The code is available at: https://github.com/ShuohaoLin/KPatch.</abstract>
<identifier type="citekey">lin-etal-2024-kpatch-knowledge</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.871</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>9961</start>
<end>9973</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T KPatch: Knowledge Patch to Pre-trained Language Model for Zero-Shot Stance Detection on Social Media
%A Lin, Shuohao
%A Chen, Wei
%A Gao, Yunpeng
%A Jiang, Zhishu
%A Liao, Mengqi
%A Zhang, Zhiyu
%A Zhao, Shuyuan
%A Wan, Huaiyu
%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 lin-etal-2024-kpatch-knowledge
%X Zero-shot stance detection on social media (ZSSD-SM) aims to distinguish the attitude in tweets towards an unseen target. Previous work capture latent variables between source and target domains to perform this task, but the lack of context knowledge hinders the detection performance. Recent studies have been devoted to obtaining the accurate representation of tweets by bringing additional facts from Knowledge Graph (KG), showing promising performance. However, these knowledge injection methods still suffer from two challenges: (i) The pipeline of knowledge injection causes error accumulation and (ii) irrelevant knowledge makes them fail to understand the semantics. In this paper, we propose a novel knowledge injection method for ZSSD-SM, which adopts two training stages, namely knowledge compression and task guidance, to flexibly inject knowledge into the pre-trained language model (PLM) and adaptively expand tweets context. Specifically, in the knowledge compression stage, the latent representation of KG is reconstructed by the triplet denoising task and compressed into external matrices; while in the task guidance stage, the frozen matrices are employed to guide the PLM to adaptively extract its own context-related knowledge, and then complete the fine-tuning of the ZSSD-SM task. Extensive experiments on multiple datasets show the effectiveness of our proposed method. The code is available at: https://github.com/ShuohaoLin/KPatch.
%U https://aclanthology.org/2024.lrec-main.871
%P 9961-9973
Markdown (Informal)
[KPatch: Knowledge Patch to Pre-trained Language Model for Zero-Shot Stance Detection on Social Media](https://aclanthology.org/2024.lrec-main.871) (Lin et al., LREC-COLING 2024)
ACL
- Shuohao Lin, Wei Chen, Yunpeng Gao, Zhishu Jiang, Mengqi Liao, Zhiyu Zhang, Shuyuan Zhao, and Huaiyu Wan. 2024. KPatch: Knowledge Patch to Pre-trained Language Model for Zero-Shot Stance Detection on Social Media. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 9961–9973, Torino, Italia. ELRA and ICCL.