@inproceedings{yavuz-etal-2020-simple,
title = "Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging",
author = "Yavuz, Semih and
Hashimoto, Kazuma and
Liu, Wenhao and
Keskar, Nitish Shirish and
Socher, Richard and
Xiong, Caiming",
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.412",
doi = "10.18653/v1/2020.emnlp-main.412",
pages = "5083--5089",
abstract = "The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of {``}request{''} carries the same speaker intention whether it is for restaurant reservation or flight booking. However, DA taggers trained on one domain do not generalize well to other domains, which leaves us with the expensive need for a large amount of annotated data in the target domain. In this work, we investigate how to better adapt DA taggers to desired target domains with only unlabeled data. We propose MaskAugment, a controllable mechanism that augments text input by leveraging the pre-trained Mask token from BERT model. Inspired by consistency regularization, we use MaskAugment to introduce an unsupervised teacher-student learning scheme to examine the domain adaptation of DA taggers. Our extensive experiments on the Simulated Dialogue (GSim) and Schema-Guided Dialogue (SGD) datasets show that MaskAugment is useful in improving the cross-domain generalization for DA tagging.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="yavuz-etal-2020-simple">
<titleInfo>
<title>Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging</title>
</titleInfo>
<name type="personal">
<namePart type="given">Semih</namePart>
<namePart type="family">Yavuz</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kazuma</namePart>
<namePart type="family">Hashimoto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenhao</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nitish</namePart>
<namePart type="given">Shirish</namePart>
<namePart type="family">Keskar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="family">Socher</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caiming</namePart>
<namePart type="family">Xiong</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>The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of “request” carries the same speaker intention whether it is for restaurant reservation or flight booking. However, DA taggers trained on one domain do not generalize well to other domains, which leaves us with the expensive need for a large amount of annotated data in the target domain. In this work, we investigate how to better adapt DA taggers to desired target domains with only unlabeled data. We propose MaskAugment, a controllable mechanism that augments text input by leveraging the pre-trained Mask token from BERT model. Inspired by consistency regularization, we use MaskAugment to introduce an unsupervised teacher-student learning scheme to examine the domain adaptation of DA taggers. Our extensive experiments on the Simulated Dialogue (GSim) and Schema-Guided Dialogue (SGD) datasets show that MaskAugment is useful in improving the cross-domain generalization for DA tagging.</abstract>
<identifier type="citekey">yavuz-etal-2020-simple</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.412</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.412</url>
</location>
<part>
<date>2020-11</date>
<extent unit="page">
<start>5083</start>
<end>5089</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging
%A Yavuz, Semih
%A Hashimoto, Kazuma
%A Liu, Wenhao
%A Keskar, Nitish Shirish
%A Socher, Richard
%A Xiong, Caiming
%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 yavuz-etal-2020-simple
%X The concept of Dialogue Act (DA) is universal across different task-oriented dialogue domains - the act of “request” carries the same speaker intention whether it is for restaurant reservation or flight booking. However, DA taggers trained on one domain do not generalize well to other domains, which leaves us with the expensive need for a large amount of annotated data in the target domain. In this work, we investigate how to better adapt DA taggers to desired target domains with only unlabeled data. We propose MaskAugment, a controllable mechanism that augments text input by leveraging the pre-trained Mask token from BERT model. Inspired by consistency regularization, we use MaskAugment to introduce an unsupervised teacher-student learning scheme to examine the domain adaptation of DA taggers. Our extensive experiments on the Simulated Dialogue (GSim) and Schema-Guided Dialogue (SGD) datasets show that MaskAugment is useful in improving the cross-domain generalization for DA tagging.
%R 10.18653/v1/2020.emnlp-main.412
%U https://aclanthology.org/2020.emnlp-main.412
%U https://doi.org/10.18653/v1/2020.emnlp-main.412
%P 5083-5089
Markdown (Informal)
[Simple Data Augmentation with the Mask Token Improves Domain Adaptation for Dialog Act Tagging](https://aclanthology.org/2020.emnlp-main.412) (Yavuz et al., EMNLP 2020)
ACL