@inproceedings{gu-etal-2021-pral,
title = "{PRAL}: A Tailored Pre-Training Model for Task-Oriented Dialog Generation",
author = "Gu, Jing and
Wu, Qingyang and
Wu, Chongruo and
Shi, Weiyan and
Yu, Zhou",
editor = "Zong, Chengqing and
Xia, Fei and
Li, Wenjie and
Navigli, Roberto",
booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-short.40",
doi = "10.18653/v1/2021.acl-short.40",
pages = "305--313",
abstract = "Large pre-trained language generation models such as GPT-2 have demonstrated their effectiveness as language priors by reaching state-of-the-art results in various language generation tasks. However, the performance of pre-trained models on task-oriented dialog tasks is still under-explored. We propose a Pre-trainedRole Alternating Language model (PRAL), explicitly designed for task-oriented conversational systems. We design several techniques: start position randomization, knowledge distillation, and history discount to improve pre-training performance. In addition, we introduce a high-quality large-scale task-oriented dialog pre-training dataset by post-prossessing13 dialog datasets. We effectively adapt PRALon three downstream tasks. The results show that PRAL outperforms or is on par with state-of-the-art models.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="gu-etal-2021-pral">
<titleInfo>
<title>PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jing</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chongruo</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyan</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Zong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fei</namePart>
<namePart type="family">Xia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenjie</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roberto</namePart>
<namePart type="family">Navigli</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>Large pre-trained language generation models such as GPT-2 have demonstrated their effectiveness as language priors by reaching state-of-the-art results in various language generation tasks. However, the performance of pre-trained models on task-oriented dialog tasks is still under-explored. We propose a Pre-trainedRole Alternating Language model (PRAL), explicitly designed for task-oriented conversational systems. We design several techniques: start position randomization, knowledge distillation, and history discount to improve pre-training performance. In addition, we introduce a high-quality large-scale task-oriented dialog pre-training dataset by post-prossessing13 dialog datasets. We effectively adapt PRALon three downstream tasks. The results show that PRAL outperforms or is on par with state-of-the-art models.</abstract>
<identifier type="citekey">gu-etal-2021-pral</identifier>
<identifier type="doi">10.18653/v1/2021.acl-short.40</identifier>
<location>
<url>https://aclanthology.org/2021.acl-short.40</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>305</start>
<end>313</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation
%A Gu, Jing
%A Wu, Qingyang
%A Wu, Chongruo
%A Shi, Weiyan
%A Yu, Zhou
%Y Zong, Chengqing
%Y Xia, Fei
%Y Li, Wenjie
%Y Navigli, Roberto
%S Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F gu-etal-2021-pral
%X Large pre-trained language generation models such as GPT-2 have demonstrated their effectiveness as language priors by reaching state-of-the-art results in various language generation tasks. However, the performance of pre-trained models on task-oriented dialog tasks is still under-explored. We propose a Pre-trainedRole Alternating Language model (PRAL), explicitly designed for task-oriented conversational systems. We design several techniques: start position randomization, knowledge distillation, and history discount to improve pre-training performance. In addition, we introduce a high-quality large-scale task-oriented dialog pre-training dataset by post-prossessing13 dialog datasets. We effectively adapt PRALon three downstream tasks. The results show that PRAL outperforms or is on par with state-of-the-art models.
%R 10.18653/v1/2021.acl-short.40
%U https://aclanthology.org/2021.acl-short.40
%U https://doi.org/10.18653/v1/2021.acl-short.40
%P 305-313
Markdown (Informal)
[PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation](https://aclanthology.org/2021.acl-short.40) (Gu et al., ACL-IJCNLP 2021)
ACL
- Jing Gu, Qingyang Wu, Chongruo Wu, Weiyan Shi, and Zhou Yu. 2021. PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 2: Short Papers), pages 305–313, Online. Association for Computational Linguistics.