@inproceedings{andreas-2020-good,
title = "Good-Enough Compositional Data Augmentation",
author = "Andreas, Jacob",
booktitle = "Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.acl-main.676",
doi = "10.18653/v1/2020.acl-main.676",
pages = "7556--7566",
abstract = "We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training examples and replacing (possibly discontinuous) fragments with other fragments that appear in at least one similar environment. The protocol is model-agnostic and useful for a variety of tasks. Applied to neural sequence-to-sequence models, it reduces error rate by as much as 87{\%} on diagnostic tasks from the SCAN dataset and 16{\%} on a semantic parsing task. Applied to n-gram language models, it reduces perplexity by roughly 1{\%} on small corpora in several languages.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="andreas-2020-good">
<titleInfo>
<title>Good-Enough Compositional Data Augmentation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jacob</namePart>
<namePart type="family">Andreas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training examples and replacing (possibly discontinuous) fragments with other fragments that appear in at least one similar environment. The protocol is model-agnostic and useful for a variety of tasks. Applied to neural sequence-to-sequence models, it reduces error rate by as much as 87% on diagnostic tasks from the SCAN dataset and 16% on a semantic parsing task. Applied to n-gram language models, it reduces perplexity by roughly 1% on small corpora in several languages.</abstract>
<identifier type="citekey">andreas-2020-good</identifier>
<identifier type="doi">10.18653/v1/2020.acl-main.676</identifier>
<location>
<url>https://aclanthology.org/2020.acl-main.676</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>7556</start>
<end>7566</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Good-Enough Compositional Data Augmentation
%A Andreas, Jacob
%S Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F andreas-2020-good
%X We propose a simple data augmentation protocol aimed at providing a compositional inductive bias in conditional and unconditional sequence models. Under this protocol, synthetic training examples are constructed by taking real training examples and replacing (possibly discontinuous) fragments with other fragments that appear in at least one similar environment. The protocol is model-agnostic and useful for a variety of tasks. Applied to neural sequence-to-sequence models, it reduces error rate by as much as 87% on diagnostic tasks from the SCAN dataset and 16% on a semantic parsing task. Applied to n-gram language models, it reduces perplexity by roughly 1% on small corpora in several languages.
%R 10.18653/v1/2020.acl-main.676
%U https://aclanthology.org/2020.acl-main.676
%U https://doi.org/10.18653/v1/2020.acl-main.676
%P 7556-7566
Markdown (Informal)
[Good-Enough Compositional Data Augmentation](https://aclanthology.org/2020.acl-main.676) (Andreas, ACL 2020)
ACL
- Jacob Andreas. 2020. Good-Enough Compositional Data Augmentation. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pages 7556–7566, Online. Association for Computational Linguistics.