@inproceedings{niu-bansal-2019-automatically,
title = "Automatically Learning Data Augmentation Policies for Dialogue Tasks",
author = "Niu, Tong and
Bansal, Mohit",
editor = "Inui, Kentaro and
Jiang, Jing and
Ng, Vincent and
Wan, Xiaojun",
booktitle = "Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)",
month = nov,
year = "2019",
address = "Hong Kong, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/D19-1132/",
doi = "10.18653/v1/D19-1132",
pages = "1317--1323",
abstract = "Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While being a powerful algorithm, their work has focused on computer vision tasks, where it is comparatively easy to apply imperceptible perturbations without changing an image's semantic meaning. In our work, we adapt AutoAugment to automatically discover effective perturbation policies for natural language processing (NLP) tasks such as dialogue generation. We start with a pool of atomic operations that apply subtle semantic-preserving perturbations to the source inputs of a dialogue task (e.g., different POS-tag types of stopword dropout, grammatical errors, and paraphrasing). Next, we allow the controller to learn more complex augmentation policies by searching over the space of the various combinations of these atomic operations. Moreover, we also explore conditioning the controller on the source inputs of the target task, since certain strategies may not apply to inputs that do not contain that strategy's required linguistic features. Empirically, we demonstrate that both our input-agnostic and input-aware controllers discover useful data augmentation policies, and achieve significant improvements over the previous state-of-the-art, including trained on manually-designed policies."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="niu-bansal-2019-automatically">
<titleInfo>
<title>Automatically Learning Data Augmentation Policies for Dialogue Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Niu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohit</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kentaro</namePart>
<namePart type="family">Inui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Jiang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincent</namePart>
<namePart type="family">Ng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaojun</namePart>
<namePart type="family">Wan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hong Kong, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While being a powerful algorithm, their work has focused on computer vision tasks, where it is comparatively easy to apply imperceptible perturbations without changing an image’s semantic meaning. In our work, we adapt AutoAugment to automatically discover effective perturbation policies for natural language processing (NLP) tasks such as dialogue generation. We start with a pool of atomic operations that apply subtle semantic-preserving perturbations to the source inputs of a dialogue task (e.g., different POS-tag types of stopword dropout, grammatical errors, and paraphrasing). Next, we allow the controller to learn more complex augmentation policies by searching over the space of the various combinations of these atomic operations. Moreover, we also explore conditioning the controller on the source inputs of the target task, since certain strategies may not apply to inputs that do not contain that strategy’s required linguistic features. Empirically, we demonstrate that both our input-agnostic and input-aware controllers discover useful data augmentation policies, and achieve significant improvements over the previous state-of-the-art, including trained on manually-designed policies.</abstract>
<identifier type="citekey">niu-bansal-2019-automatically</identifier>
<identifier type="doi">10.18653/v1/D19-1132</identifier>
<location>
<url>https://aclanthology.org/D19-1132/</url>
</location>
<part>
<date>2019-11</date>
<extent unit="page">
<start>1317</start>
<end>1323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatically Learning Data Augmentation Policies for Dialogue Tasks
%A Niu, Tong
%A Bansal, Mohit
%Y Inui, Kentaro
%Y Jiang, Jing
%Y Ng, Vincent
%Y Wan, Xiaojun
%S Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)
%D 2019
%8 November
%I Association for Computational Linguistics
%C Hong Kong, China
%F niu-bansal-2019-automatically
%X Automatic data augmentation (AutoAugment) (Cubuk et al., 2019) searches for optimal perturbation policies via a controller trained using performance rewards of a sampled policy on the target task, hence reducing data-level model bias. While being a powerful algorithm, their work has focused on computer vision tasks, where it is comparatively easy to apply imperceptible perturbations without changing an image’s semantic meaning. In our work, we adapt AutoAugment to automatically discover effective perturbation policies for natural language processing (NLP) tasks such as dialogue generation. We start with a pool of atomic operations that apply subtle semantic-preserving perturbations to the source inputs of a dialogue task (e.g., different POS-tag types of stopword dropout, grammatical errors, and paraphrasing). Next, we allow the controller to learn more complex augmentation policies by searching over the space of the various combinations of these atomic operations. Moreover, we also explore conditioning the controller on the source inputs of the target task, since certain strategies may not apply to inputs that do not contain that strategy’s required linguistic features. Empirically, we demonstrate that both our input-agnostic and input-aware controllers discover useful data augmentation policies, and achieve significant improvements over the previous state-of-the-art, including trained on manually-designed policies.
%R 10.18653/v1/D19-1132
%U https://aclanthology.org/D19-1132/
%U https://doi.org/10.18653/v1/D19-1132
%P 1317-1323
Markdown (Informal)
[Automatically Learning Data Augmentation Policies for Dialogue Tasks](https://aclanthology.org/D19-1132/) (Niu & Bansal, EMNLP-IJCNLP 2019)
ACL
- Tong Niu and Mohit Bansal. 2019. Automatically Learning Data Augmentation Policies for Dialogue Tasks. In Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pages 1317–1323, Hong Kong, China. Association for Computational Linguistics.