@inproceedings{ontanon-etal-2022-making,
title = "Making Transformers Solve Compositional Tasks",
author = "Ontanon, Santiago and
Ainslie, Joshua and
Fisher, Zachary and
Cvicek, Vaclav",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.acl-long.251",
doi = "10.18653/v1/2022.acl-long.251",
pages = "3591--3607",
abstract = "Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Transformer models showing that the inductive biases given to the model by several design decisions significantly impact compositional generalization. We identified Transformer configurations that generalize compositionally significantly better than previously reported in the literature in many compositional tasks. We achieve state-of-the-art results in a semantic parsing compositional generalization benchmark (COGS), and a string edit operation composition benchmark (PCFG).",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ontanon-etal-2022-making">
<titleInfo>
<title>Making Transformers Solve Compositional Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Ontanon</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joshua</namePart>
<namePart type="family">Ainslie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zachary</namePart>
<namePart type="family">Fisher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vaclav</namePart>
<namePart type="family">Cvicek</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 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</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>Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Transformer models showing that the inductive biases given to the model by several design decisions significantly impact compositional generalization. We identified Transformer configurations that generalize compositionally significantly better than previously reported in the literature in many compositional tasks. We achieve state-of-the-art results in a semantic parsing compositional generalization benchmark (COGS), and a string edit operation composition benchmark (PCFG).</abstract>
<identifier type="citekey">ontanon-etal-2022-making</identifier>
<identifier type="doi">10.18653/v1/2022.acl-long.251</identifier>
<location>
<url>https://aclanthology.org/2022.acl-long.251</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>3591</start>
<end>3607</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Making Transformers Solve Compositional Tasks
%A Ontanon, Santiago
%A Ainslie, Joshua
%A Fisher, Zachary
%A Cvicek, Vaclav
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F ontanon-etal-2022-making
%X Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing. In this paper we explore the design space of Transformer models showing that the inductive biases given to the model by several design decisions significantly impact compositional generalization. We identified Transformer configurations that generalize compositionally significantly better than previously reported in the literature in many compositional tasks. We achieve state-of-the-art results in a semantic parsing compositional generalization benchmark (COGS), and a string edit operation composition benchmark (PCFG).
%R 10.18653/v1/2022.acl-long.251
%U https://aclanthology.org/2022.acl-long.251
%U https://doi.org/10.18653/v1/2022.acl-long.251
%P 3591-3607
Markdown (Informal)
[Making Transformers Solve Compositional Tasks](https://aclanthology.org/2022.acl-long.251) (Ontanon et al., ACL 2022)
ACL
- Santiago Ontanon, Joshua Ainslie, Zachary Fisher, and Vaclav Cvicek. 2022. Making Transformers Solve Compositional Tasks. In Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 3591–3607, Dublin, Ireland. Association for Computational Linguistics.