@inproceedings{lal-etal-2022-using,
title = "Using Commonsense Knowledge to Answer Why-Questions",
author = "Lal, Yash Kumar and
Tandon, Niket and
Aggarwal, Tanvi and
Liu, Horace and
Chambers, Nathanael and
Mooney, Raymond and
Balasubramanian, Niranjan",
editor = "Goldberg, Yoav and
Kozareva, Zornitsa and
Zhang, Yue",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2022",
address = "Abu Dhabi, United Arab Emirates",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-main.79",
doi = "10.18653/v1/2022.emnlp-main.79",
pages = "1204--1219",
abstract = "Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TellMeWhy dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 and GPT3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models. Injecting external knowledge helps models of various sizes, but the amount of improvement decreases with larger model size. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="lal-etal-2022-using">
<titleInfo>
<title>Using Commonsense Knowledge to Answer Why-Questions</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yash</namePart>
<namePart type="given">Kumar</namePart>
<namePart type="family">Lal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niket</namePart>
<namePart type="family">Tandon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanvi</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Horace</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nathanael</namePart>
<namePart type="family">Chambers</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Raymond</namePart>
<namePart type="family">Mooney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Niranjan</namePart>
<namePart type="family">Balasubramanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yoav</namePart>
<namePart type="family">Goldberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zornitsa</namePart>
<namePart type="family">Kozareva</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, United Arab Emirates</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TellMeWhy dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 and GPT3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models. Injecting external knowledge helps models of various sizes, but the amount of improvement decreases with larger model size. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.</abstract>
<identifier type="citekey">lal-etal-2022-using</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-main.79</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-main.79</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>1204</start>
<end>1219</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Commonsense Knowledge to Answer Why-Questions
%A Lal, Yash Kumar
%A Tandon, Niket
%A Aggarwal, Tanvi
%A Liu, Horace
%A Chambers, Nathanael
%A Mooney, Raymond
%A Balasubramanian, Niranjan
%Y Goldberg, Yoav
%Y Kozareva, Zornitsa
%Y Zhang, Yue
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, United Arab Emirates
%F lal-etal-2022-using
%X Answering questions in narratives about why events happened often requires commonsense knowledge external to the text. What aspects of this knowledge are available in large language models? What aspects can be made accessible via external commonsense resources? We study these questions in the context of answering questions in the TellMeWhy dataset using COMET as a source of relevant commonsense relations. We analyze the effects of model size (T5 and GPT3) along with methods of injecting knowledge (COMET) into these models. Results show that the largest models, as expected, yield substantial improvements over base models. Injecting external knowledge helps models of various sizes, but the amount of improvement decreases with larger model size. We also find that the format in which knowledge is provided is critical, and that smaller models benefit more from larger amounts of knowledge. Finally, we develop an ontology of knowledge types and analyze the relative coverage of the models across these categories.
%R 10.18653/v1/2022.emnlp-main.79
%U https://aclanthology.org/2022.emnlp-main.79
%U https://doi.org/10.18653/v1/2022.emnlp-main.79
%P 1204-1219
Markdown (Informal)
[Using Commonsense Knowledge to Answer Why-Questions](https://aclanthology.org/2022.emnlp-main.79) (Lal et al., EMNLP 2022)
ACL
- Yash Kumar Lal, Niket Tandon, Tanvi Aggarwal, Horace Liu, Nathanael Chambers, Raymond Mooney, and Niranjan Balasubramanian. 2022. Using Commonsense Knowledge to Answer Why-Questions. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pages 1204–1219, Abu Dhabi, United Arab Emirates. Association for Computational Linguistics.