@inproceedings{yao-koller-2024-simple,
title = "Simple and effective data augmentation for compositional generalization",
author = "Yao, Yuekun and
Koller, Alexander",
editor = "Duh, Kevin and
Gomez, Helena and
Bethard, Steven",
booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
month = jun,
year = "2024",
address = "Mexico City, Mexico",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.naacl-long.25",
doi = "10.18653/v1/2024.naacl-long.25",
pages = "434--449",
abstract = "Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models. In this paper, we show that data augmentation methods that sample MRs and backtranslate them can be effective for compositional generalization, but only if we sample from the right distribution. Remarkably, sampling from a uniform distribution performs almost as well as sampling from the test distribution, and greatly outperforms earlier methods that sampled from the training distribution.We further conduct experiments to investigate the reason why this happens and where the benefit of such data augmentation methods come from.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yao-koller-2024-simple">
<titleInfo>
<title>Simple and effective data augmentation for compositional generalization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yuekun</namePart>
<namePart type="family">Yao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Koller</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kevin</namePart>
<namePart type="family">Duh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Helena</namePart>
<namePart type="family">Gomez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Mexico City, Mexico</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models. In this paper, we show that data augmentation methods that sample MRs and backtranslate them can be effective for compositional generalization, but only if we sample from the right distribution. Remarkably, sampling from a uniform distribution performs almost as well as sampling from the test distribution, and greatly outperforms earlier methods that sampled from the training distribution.We further conduct experiments to investigate the reason why this happens and where the benefit of such data augmentation methods come from.</abstract>
<identifier type="citekey">yao-koller-2024-simple</identifier>
<identifier type="doi">10.18653/v1/2024.naacl-long.25</identifier>
<location>
<url>https://aclanthology.org/2024.naacl-long.25</url>
</location>
<part>
<date>2024-06</date>
<extent unit="page">
<start>434</start>
<end>449</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple and effective data augmentation for compositional generalization
%A Yao, Yuekun
%A Koller, Alexander
%Y Duh, Kevin
%Y Gomez, Helena
%Y Bethard, Steven
%S Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)
%D 2024
%8 June
%I Association for Computational Linguistics
%C Mexico City, Mexico
%F yao-koller-2024-simple
%X Compositional generalization, the ability to predict complex meanings from training on simpler sentences, poses challenges for powerful pretrained seq2seq models. In this paper, we show that data augmentation methods that sample MRs and backtranslate them can be effective for compositional generalization, but only if we sample from the right distribution. Remarkably, sampling from a uniform distribution performs almost as well as sampling from the test distribution, and greatly outperforms earlier methods that sampled from the training distribution.We further conduct experiments to investigate the reason why this happens and where the benefit of such data augmentation methods come from.
%R 10.18653/v1/2024.naacl-long.25
%U https://aclanthology.org/2024.naacl-long.25
%U https://doi.org/10.18653/v1/2024.naacl-long.25
%P 434-449
Markdown (Informal)
[Simple and effective data augmentation for compositional generalization](https://aclanthology.org/2024.naacl-long.25) (Yao & Koller, NAACL 2024)
ACL
- Yuekun Yao and Alexander Koller. 2024. Simple and effective data augmentation for compositional generalization. In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers), pages 434–449, Mexico City, Mexico. Association for Computational Linguistics.