@inproceedings{petersen-van-der-plas-2023-language,
title = "Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance",
author = "Petersen, Molly and
van der Plas, Lonneke",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.emnlp-main.1022",
doi = "10.18653/v1/2023.emnlp-main.1022",
pages = "16414--16425",
abstract = "While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned. In this paper, we test several ways to learn basic analogical reasoning, specifically focusing on analogies that are more typical of what is used to evaluate analogical reasoning in humans than those in commonly used NLP benchmarks. Our experiments find that models are able to learn analogical reasoning, even with a small amount of data. We additionally compare our models to a dataset with a human baseline, and find that after training models approach human performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petersen-van-der-plas-2023-language">
<titleInfo>
<title>Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance</title>
</titleInfo>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Petersen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lonneke</namePart>
<namePart type="family">van der Plas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned. In this paper, we test several ways to learn basic analogical reasoning, specifically focusing on analogies that are more typical of what is used to evaluate analogical reasoning in humans than those in commonly used NLP benchmarks. Our experiments find that models are able to learn analogical reasoning, even with a small amount of data. We additionally compare our models to a dataset with a human baseline, and find that after training models approach human performance.</abstract>
<identifier type="citekey">petersen-van-der-plas-2023-language</identifier>
<identifier type="doi">10.18653/v1/2023.emnlp-main.1022</identifier>
<location>
<url>https://aclanthology.org/2023.emnlp-main.1022</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>16414</start>
<end>16425</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance
%A Petersen, Molly
%A van der Plas, Lonneke
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F petersen-van-der-plas-2023-language
%X While analogies are a common way to evaluate word embeddings in NLP, it is also of interest to investigate whether or not analogical reasoning is a task in itself that can be learned. In this paper, we test several ways to learn basic analogical reasoning, specifically focusing on analogies that are more typical of what is used to evaluate analogical reasoning in humans than those in commonly used NLP benchmarks. Our experiments find that models are able to learn analogical reasoning, even with a small amount of data. We additionally compare our models to a dataset with a human baseline, and find that after training models approach human performance.
%R 10.18653/v1/2023.emnlp-main.1022
%U https://aclanthology.org/2023.emnlp-main.1022
%U https://doi.org/10.18653/v1/2023.emnlp-main.1022
%P 16414-16425
Markdown (Informal)
[Can language models learn analogical reasoning? Investigating training objectives and comparisons to human performance](https://aclanthology.org/2023.emnlp-main.1022) (Petersen & van der Plas, EMNLP 2023)
ACL