@inproceedings{cazzaro-etal-2024-align,
title = "Align and Augment: Generative Data Augmentation for Compositional Generalization",
author = "Cazzaro, Francesco and
Locatelli, Davide and
Quattoni, Ariadna",
editor = "Graham, Yvette and
Purver, Matthew",
booktitle = "Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)",
month = mar,
year = "2024",
address = "St. Julian{'}s, Malta",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.eacl-long.22",
pages = "369--383",
abstract = "Recent work on semantic parsing has shown that seq2seq models find compositional generalization challenging. Several strategies have been proposed to mitigate this challenge. One such strategy is to improve compositional generalization via data augmentation techniques. In this paper we follow this line of work and propose Archer, a data-augmentation strategy that exploits alignment annotations between sentences and their corresponding meaning representations. More precisely, we use alignments to train a two step generative model that combines monotonic lexical generation with reordering. Our experiments show that Archer leads to significant improvements in compositional generalization performance.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="cazzaro-etal-2024-align">
<titleInfo>
<title>Align and Augment: Generative Data Augmentation for Compositional Generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Francesco</namePart>
<namePart type="family">Cazzaro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Davide</namePart>
<namePart type="family">Locatelli</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ariadna</namePart>
<namePart type="family">Quattoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-03</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yvette</namePart>
<namePart type="family">Graham</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="family">Purver</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">St. Julian’s, Malta</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Recent work on semantic parsing has shown that seq2seq models find compositional generalization challenging. Several strategies have been proposed to mitigate this challenge. One such strategy is to improve compositional generalization via data augmentation techniques. In this paper we follow this line of work and propose Archer, a data-augmentation strategy that exploits alignment annotations between sentences and their corresponding meaning representations. More precisely, we use alignments to train a two step generative model that combines monotonic lexical generation with reordering. Our experiments show that Archer leads to significant improvements in compositional generalization performance.</abstract>
<identifier type="citekey">cazzaro-etal-2024-align</identifier>
<location>
<url>https://aclanthology.org/2024.eacl-long.22</url>
</location>
<part>
<date>2024-03</date>
<extent unit="page">
<start>369</start>
<end>383</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Align and Augment: Generative Data Augmentation for Compositional Generalization
%A Cazzaro, Francesco
%A Locatelli, Davide
%A Quattoni, Ariadna
%Y Graham, Yvette
%Y Purver, Matthew
%S Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2024
%8 March
%I Association for Computational Linguistics
%C St. Julian’s, Malta
%F cazzaro-etal-2024-align
%X Recent work on semantic parsing has shown that seq2seq models find compositional generalization challenging. Several strategies have been proposed to mitigate this challenge. One such strategy is to improve compositional generalization via data augmentation techniques. In this paper we follow this line of work and propose Archer, a data-augmentation strategy that exploits alignment annotations between sentences and their corresponding meaning representations. More precisely, we use alignments to train a two step generative model that combines monotonic lexical generation with reordering. Our experiments show that Archer leads to significant improvements in compositional generalization performance.
%U https://aclanthology.org/2024.eacl-long.22
%P 369-383
Markdown (Informal)
[Align and Augment: Generative Data Augmentation for Compositional Generalization](https://aclanthology.org/2024.eacl-long.22) (Cazzaro et al., EACL 2024)
ACL