@inproceedings{ding-etal-2020-daga,
title = "{DAGA}: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks",
author = "Ding, Bosheng and
Liu, Linlin and
Bing, Lidong and
Kruengkrai, Canasai and
Nguyen, Thien Hai and
Joty, Shafiq and
Si, Luo and
Miao, Chunyan",
editor = "Webber, Bonnie and
Cohn, Trevor and
He, Yulan and
Liu, Yang",
booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
month = nov,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.emnlp-main.488/",
doi = "10.18653/v1/2020.emnlp-main.488",
pages = "6045--6057",
abstract = "Data augmentation techniques have been widely used to improve machine learning performance as they facilitate generalization. In this work, we propose a novel augmentation method to generate high quality synthetic data for low-resource tagging tasks with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tasks. For the semi-supervised settings, we evaluate our method on the NER task under the conditions of given unlabeled data only and unlabeled data plus a knowledge base. The results show that our method can consistently outperform the baselines, particularly when the given gold training data are less."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ding-etal-2020-daga">
<titleInfo>
<title>DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bosheng</namePart>
<namePart type="family">Ding</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linlin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lidong</namePart>
<namePart type="family">Bing</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Canasai</namePart>
<namePart type="family">Kruengkrai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thien</namePart>
<namePart type="given">Hai</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shafiq</namePart>
<namePart type="family">Joty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luo</namePart>
<namePart type="family">Si</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chunyan</namePart>
<namePart type="family">Miao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bonnie</namePart>
<namePart type="family">Webber</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Trevor</namePart>
<namePart type="family">Cohn</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yulan</namePart>
<namePart type="family">He</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Data augmentation techniques have been widely used to improve machine learning performance as they facilitate generalization. In this work, we propose a novel augmentation method to generate high quality synthetic data for low-resource tagging tasks with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tasks. For the semi-supervised settings, we evaluate our method on the NER task under the conditions of given unlabeled data only and unlabeled data plus a knowledge base. The results show that our method can consistently outperform the baselines, particularly when the given gold training data are less.</abstract>
<identifier type="citekey">ding-etal-2020-daga</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.488</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.488/</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>6045</start>
<end>6057</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks
%A Ding, Bosheng
%A Liu, Linlin
%A Bing, Lidong
%A Kruengkrai, Canasai
%A Nguyen, Thien Hai
%A Joty, Shafiq
%A Si, Luo
%A Miao, Chunyan
%Y Webber, Bonnie
%Y Cohn, Trevor
%Y He, Yulan
%Y Liu, Yang
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 November
%I Association for Computational Linguistics
%C Online
%F ding-etal-2020-daga
%X Data augmentation techniques have been widely used to improve machine learning performance as they facilitate generalization. In this work, we propose a novel augmentation method to generate high quality synthetic data for low-resource tagging tasks with language models trained on the linearized labeled sentences. Our method is applicable to both supervised and semi-supervised settings. For the supervised settings, we conduct extensive experiments on named entity recognition (NER), part of speech (POS) tagging and end-to-end target based sentiment analysis (E2E-TBSA) tasks. For the semi-supervised settings, we evaluate our method on the NER task under the conditions of given unlabeled data only and unlabeled data plus a knowledge base. The results show that our method can consistently outperform the baselines, particularly when the given gold training data are less.
%R 10.18653/v1/2020.emnlp-main.488
%U https://aclanthology.org/2020.emnlp-main.488/
%U https://doi.org/10.18653/v1/2020.emnlp-main.488
%P 6045-6057
Markdown (Informal)
[DAGA: Data Augmentation with a Generation Approach for Low-resource Tagging Tasks](https://aclanthology.org/2020.emnlp-main.488/) (Ding et al., EMNLP 2020)
ACL