@inproceedings{jiang-etal-2022-great,
title = "$Great~Truths~are ~Always ~Simple:$ A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models",
author = "Jiang, Jinhao and
Zhou, Kun and
Wen, Ji-Rong and
Zhao, Xin",
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.131",
doi = "10.18653/v1/2022.findings-naacl.131",
pages = "1730--1741",
abstract = "Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models (PTMs) with a knowledge-aware graph neural network (GNN) encoder that models a commonsense knowledge graph (CSKG).Despite the effectiveness, these approaches are built on heavy architectures, and can{'}t clearly explain how external knowledge resources improve the reasoning capacity of PTMs. Considering this issue, we conduct a deep empirical analysis, and find that it is indeed \textit{relation features} from CSKGs (but not \textit{node features}) that mainly contribute to the performance improvement of PTMs. Based on this finding, we design a simple MLP-based knowledge encoder that utilizes statistical relation paths as features. Extensive experiments conducted on five benchmarks demonstrate the effectiveness of our approach, which also largely reduces the parameters for encoding CSKGs.Our codes and data are publicly available at \url{https://github.com/RUCAIBox/SAFE}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jiang-etal-2022-great">
<titleInfo>
<title>Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinhao</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kun</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ji-Rong</namePart>
<namePart type="family">Wen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Zhao</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>Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models (PTMs) with a knowledge-aware graph neural network (GNN) encoder that models a commonsense knowledge graph (CSKG).Despite the effectiveness, these approaches are built on heavy architectures, and can’t clearly explain how external knowledge resources improve the reasoning capacity of PTMs. Considering this issue, we conduct a deep empirical analysis, and find that it is indeed relation features from CSKGs (but not node features) that mainly contribute to the performance improvement of PTMs. Based on this finding, we design a simple MLP-based knowledge encoder that utilizes statistical relation paths as features. Extensive experiments conducted on five benchmarks demonstrate the effectiveness of our approach, which also largely reduces the parameters for encoding CSKGs.Our codes and data are publicly available at https://github.com/RUCAIBox/SAFE.</abstract>
<identifier type="citekey">jiang-etal-2022-great</identifier>
<identifier type="doi">10.18653/v1/2022.findings-naacl.131</identifier>
<location>
<url>https://aclanthology.org/2022.findings-naacl.131</url>
</location>
<part>
<date>2022-07</date>
<extent unit="page">
<start>1730</start>
<end>1741</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Great Truths are Always Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models
%A Jiang, Jinhao
%A Zhou, Kun
%A Wen, Ji-Rong
%A Zhao, Xin
%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 jiang-etal-2022-great
%X Commonsense reasoning in natural language is a desired ability of artificial intelligent systems. For solving complex commonsense reasoning tasks, a typical solution is to enhance pre-trained language models (PTMs) with a knowledge-aware graph neural network (GNN) encoder that models a commonsense knowledge graph (CSKG).Despite the effectiveness, these approaches are built on heavy architectures, and can’t clearly explain how external knowledge resources improve the reasoning capacity of PTMs. Considering this issue, we conduct a deep empirical analysis, and find that it is indeed relation features from CSKGs (but not node features) that mainly contribute to the performance improvement of PTMs. Based on this finding, we design a simple MLP-based knowledge encoder that utilizes statistical relation paths as features. Extensive experiments conducted on five benchmarks demonstrate the effectiveness of our approach, which also largely reduces the parameters for encoding CSKGs.Our codes and data are publicly available at https://github.com/RUCAIBox/SAFE.
%R 10.18653/v1/2022.findings-naacl.131
%U https://aclanthology.org/2022.findings-naacl.131
%U https://doi.org/10.18653/v1/2022.findings-naacl.131
%P 1730-1741
Markdown (Informal)
[Great~Truths~are ~Always ~Simple: A Rather Simple Knowledge Encoder for Enhancing the Commonsense Reasoning Capacity of Pre-Trained Models](https://aclanthology.org/2022.findings-naacl.131) (Jiang et al., Findings 2022)
ACL