@inproceedings{mi-etal-2021-self,
title = "Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems",
author = "Mi, Fei and
Zhou, Wanhao and
Kong, Lingjing and
Cai, Fengyu and
Huang, Minlie and
Faltings, Boi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.142",
doi = "10.18653/v1/2021.emnlp-main.142",
pages = "1887--1898",
abstract = "As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have shown promising results for few-shot learning in ToD. In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems. Specifically, we propose a self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model. Moreover, a new text augmentation technique (GradAug) is proposed to better train the Student by replacing non-crucial tokens using a masked language model. We conduct extensive experiments and present analyses on four downstream tasks in ToD, including intent classification, dialog state tracking, dialog act prediction, and response selection. Empirical results demonstrate that the proposed self-training approach consistently improves state-of-the-art pre-trained models (BERT, ToD-BERT) when only a small number of labeled data are available.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="mi-etal-2021-self">
<titleInfo>
<title>Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems</title>
</titleInfo>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Mi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wanhao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lingjing</namePart>
<namePart type="family">Kong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fengyu</namePart>
<namePart type="family">Cai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minlie</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Boi</namePart>
<namePart type="family">Faltings</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have shown promising results for few-shot learning in ToD. In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems. Specifically, we propose a self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model. Moreover, a new text augmentation technique (GradAug) is proposed to better train the Student by replacing non-crucial tokens using a masked language model. We conduct extensive experiments and present analyses on four downstream tasks in ToD, including intent classification, dialog state tracking, dialog act prediction, and response selection. Empirical results demonstrate that the proposed self-training approach consistently improves state-of-the-art pre-trained models (BERT, ToD-BERT) when only a small number of labeled data are available.</abstract>
<identifier type="citekey">mi-etal-2021-self</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.142</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.142</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>1887</start>
<end>1898</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems
%A Mi, Fei
%A Zhou, Wanhao
%A Kong, Lingjing
%A Cai, Fengyu
%A Huang, Minlie
%A Faltings, Boi
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F mi-etal-2021-self
%X As the labeling cost for different modules in task-oriented dialog (ToD) systems is expensive, a major challenge is to train different modules with the least amount of labeled data. Recently, large-scale pre-trained language models, have shown promising results for few-shot learning in ToD. In this paper, we devise a self-training approach to utilize the abundant unlabeled dialog data to further improve state-of-the-art pre-trained models in few-shot learning scenarios for ToD systems. Specifically, we propose a self-training approach that iteratively labels the most confident unlabeled data to train a stronger Student model. Moreover, a new text augmentation technique (GradAug) is proposed to better train the Student by replacing non-crucial tokens using a masked language model. We conduct extensive experiments and present analyses on four downstream tasks in ToD, including intent classification, dialog state tracking, dialog act prediction, and response selection. Empirical results demonstrate that the proposed self-training approach consistently improves state-of-the-art pre-trained models (BERT, ToD-BERT) when only a small number of labeled data are available.
%R 10.18653/v1/2021.emnlp-main.142
%U https://aclanthology.org/2021.emnlp-main.142
%U https://doi.org/10.18653/v1/2021.emnlp-main.142
%P 1887-1898
Markdown (Informal)
[Self-training Improves Pre-training for Few-shot Learning in Task-oriented Dialog Systems](https://aclanthology.org/2021.emnlp-main.142) (Mi et al., EMNLP 2021)
ACL