@inproceedings{jpliu-wtu-edu-cn-etal-2022-seeing,
title = "Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering",
author = "Jpliu@wtu.edu.cn, Jpliu@wtu.edu.cn and
Mei, Shijie and
Hu, Xinrong and
Yao, Xun and
Yang, Jack and
Guo, Yi",
editor = "Carpuat, Marine and
de Marneffe, Marie-Catherine and
Meza Ruiz, Ivan Vladimir",
booktitle = "Findings of the Association for Computational Linguistics: NAACL 2022",
month = jul,
year = "2022",
address = "Seattle, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-naacl.82",
doi = "10.18653/v1/2022.findings-naacl.82",
pages = "1085--1094",
abstract = "Given a context knowledge base (KB) and a corresponding question, the Knowledge Base Question Answering task aims to retrieve correct answer entities from this KB. Despite sophisticated retrieval algorithms, the impact of the low-resource (incomplete) KB is not fully exploited, where contributing components (. key entities and/or relations) may be absent for question answering. To effectively address this problem, we propose a contrastive regularization based method, which is motivated by the learn-by-analogy capability from human readers. Specifically, the proposed work includes two major modules: the knowledge extension and sMoCo module. The former aims at exploiting the latent knowledge from the context KB and generating auxiliary information in the form of question-answer pairs. The later module utilizes those additional pairs and applies the contrastive regularization to learn informative representations, that making hard positive pairs attracted and hard negative pairs separated. Empirically, we achieved the state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jpliu-wtu-edu-cn-etal-2022-seeing">
<titleInfo>
<title>Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jpliu@wtu.edu.cn</namePart>
<namePart type="family">Jpliu@wtu.edu.cn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shijie</namePart>
<namePart type="family">Mei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinrong</namePart>
<namePart type="family">Hu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xun</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jack</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Guo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: NAACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marine</namePart>
<namePart type="family">Carpuat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marie-Catherine</namePart>
<namePart type="family">de Marneffe</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ivan</namePart>
<namePart type="given">Vladimir</namePart>
<namePart type="family">Meza Ruiz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Seattle, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Given a context knowledge base (KB) and a corresponding question, the Knowledge Base Question Answering task aims to retrieve correct answer entities from this KB. Despite sophisticated retrieval algorithms, the impact of the low-resource (incomplete) KB is not fully exploited, where contributing components (. key entities and/or relations) may be absent for question answering. To effectively address this problem, we propose a contrastive regularization based method, which is motivated by the learn-by-analogy capability from human readers. Specifically, the proposed work includes two major modules: the knowledge extension and sMoCo module. The former aims at exploiting the latent knowledge from the context KB and generating auxiliary information in the form of question-answer pairs. The later module utilizes those additional pairs and applies the contrastive regularization to learn informative representations, that making hard positive pairs attracted and hard negative pairs separated. Empirically, we achieved the state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.</abstract>
<identifier type="citekey">jpliu-wtu-edu-cn-etal-2022-seeing</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.82</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.82</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1085</start>
<end>1094</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering
%A Jpliu@wtu.edu.cn, Jpliu@wtu.edu.cn
%A Mei, Shijie
%A Hu, Xinrong
%A Yao, Xun
%A Yang, Jack
%A Guo, Yi
%Y Carpuat, Marine
%Y de Marneffe, Marie-Catherine
%Y Meza Ruiz, Ivan Vladimir
%S Findings of the Association for Computational Linguistics: NAACL 2022
%D 2022
%8 July
%I Association for Computational Linguistics
%C Seattle, United States
%F jpliu-wtu-edu-cn-etal-2022-seeing
%X Given a context knowledge base (KB) and a corresponding question, the Knowledge Base Question Answering task aims to retrieve correct answer entities from this KB. Despite sophisticated retrieval algorithms, the impact of the low-resource (incomplete) KB is not fully exploited, where contributing components (. key entities and/or relations) may be absent for question answering. To effectively address this problem, we propose a contrastive regularization based method, which is motivated by the learn-by-analogy capability from human readers. Specifically, the proposed work includes two major modules: the knowledge extension and sMoCo module. The former aims at exploiting the latent knowledge from the context KB and generating auxiliary information in the form of question-answer pairs. The later module utilizes those additional pairs and applies the contrastive regularization to learn informative representations, that making hard positive pairs attracted and hard negative pairs separated. Empirically, we achieved the state-of-the-art performance on the WebQuestionsSP dataset and the effectiveness of proposed modules is also evaluated.
%R 10.18653/v1/2022.findings-naacl.82
%U https://aclanthology.org/2022.findings-naacl.82
%U https://doi.org/10.18653/v1/2022.findings-naacl.82
%P 1085-1094
Markdown (Informal)
[Seeing the wood for the trees: a contrastive regularization method for the low-resource Knowledge Base Question Answering](https://aclanthology.org/2022.findings-naacl.82) (Jpliu@wtu.edu.cn et al., Findings 2022)
ACL