@inproceedings{hosseini-etal-2022-knowledge,
title = "Knowledge-Augmented Language Models for Cause-Effect Relation Classification",
author = "Hosseini, Pedram and
Broniatowski, David A. and
Diab, Mona",
editor = "Bosselut, Antoine and
Li, Xiang and
Lin, Bill Yuchen and
Shwartz, Vered and
Majumder, Bodhisattwa Prasad and
Lal, Yash Kumar and
Rudinger, Rachel and
Ren, Xiang and
Tandon, Niket and
Zouhar, Vil{\'e}m",
booktitle = "Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.csrr-1.6",
doi = "10.18653/v1/2022.csrr-1.6",
pages = "43--48",
abstract = "Previous studies have shown the efficacy of knowledge augmentation methods in pretrained language models. However, these methods behave differently across domains and downstream tasks. In this work, we investigate the augmentation of pretrained language models with knowledge graph data in the cause-effect relation classification and commonsense causal reasoning tasks. After automatically verbalizing triples in ATOMIC2020, a wide coverage commonsense reasoning knowledge graph, we continually pretrain BERT and evaluate the resulting model on cause-effect pair classification and answering commonsense causal reasoning questions. Our results show that a continually pretrained language model augmented with commonsense reasoning knowledge outperforms our baselines on two commonsense causal reasoning benchmarks, COPA and BCOPA-CE, and a Temporal and Causal Reasoning (TCR) dataset, without additional improvement in model architecture or using quality-enhanced data for fine-tuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hosseini-etal-2022-knowledge">
<titleInfo>
<title>Knowledge-Augmented Language Models for Cause-Effect Relation Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pedram</namePart>
<namePart type="family">Hosseini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Broniatowski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Antoine</namePart>
<namePart type="family">Bosselut</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bill</namePart>
<namePart type="given">Yuchen</namePart>
<namePart type="family">Lin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vered</namePart>
<namePart type="family">Shwartz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bodhisattwa</namePart>
<namePart type="given">Prasad</namePart>
<namePart type="family">Majumder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Lal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rachel</namePart>
<namePart type="family">Rudinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiang</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vilém</namePart>
<namePart type="family">Zouhar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Previous studies have shown the efficacy of knowledge augmentation methods in pretrained language models. However, these methods behave differently across domains and downstream tasks. In this work, we investigate the augmentation of pretrained language models with knowledge graph data in the cause-effect relation classification and commonsense causal reasoning tasks. After automatically verbalizing triples in ATOMIC2020, a wide coverage commonsense reasoning knowledge graph, we continually pretrain BERT and evaluate the resulting model on cause-effect pair classification and answering commonsense causal reasoning questions. Our results show that a continually pretrained language model augmented with commonsense reasoning knowledge outperforms our baselines on two commonsense causal reasoning benchmarks, COPA and BCOPA-CE, and a Temporal and Causal Reasoning (TCR) dataset, without additional improvement in model architecture or using quality-enhanced data for fine-tuning.</abstract>
<identifier type="citekey">hosseini-etal-2022-knowledge</identifier>
<identifier type="doi">10.18653/v1/2022.csrr-1.6</identifier>
<location>
<url>https://aclanthology.org/2022.csrr-1.6</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>43</start>
<end>48</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Knowledge-Augmented Language Models for Cause-Effect Relation Classification
%A Hosseini, Pedram
%A Broniatowski, David A.
%A Diab, Mona
%Y Bosselut, Antoine
%Y Li, Xiang
%Y Lin, Bill Yuchen
%Y Shwartz, Vered
%Y Majumder, Bodhisattwa Prasad
%Y Lal, Yash Kumar
%Y Rudinger, Rachel
%Y Ren, Xiang
%Y Tandon, Niket
%Y Zouhar, Vilém
%S Proceedings of the First Workshop on Commonsense Representation and Reasoning (CSRR 2022)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F hosseini-etal-2022-knowledge
%X Previous studies have shown the efficacy of knowledge augmentation methods in pretrained language models. However, these methods behave differently across domains and downstream tasks. In this work, we investigate the augmentation of pretrained language models with knowledge graph data in the cause-effect relation classification and commonsense causal reasoning tasks. After automatically verbalizing triples in ATOMIC2020, a wide coverage commonsense reasoning knowledge graph, we continually pretrain BERT and evaluate the resulting model on cause-effect pair classification and answering commonsense causal reasoning questions. Our results show that a continually pretrained language model augmented with commonsense reasoning knowledge outperforms our baselines on two commonsense causal reasoning benchmarks, COPA and BCOPA-CE, and a Temporal and Causal Reasoning (TCR) dataset, without additional improvement in model architecture or using quality-enhanced data for fine-tuning.
%R 10.18653/v1/2022.csrr-1.6
%U https://aclanthology.org/2022.csrr-1.6
%U https://doi.org/10.18653/v1/2022.csrr-1.6
%P 43-48
Markdown (Informal)
[Knowledge-Augmented Language Models for Cause-Effect Relation Classification](https://aclanthology.org/2022.csrr-1.6) (Hosseini et al., CSRR 2022)
ACL