@inproceedings{zhou-etal-2023-multi,
title = "Multi-Stage Pre-training Enhanced by {C}hat{GPT} for Multi-Scenario Multi-Domain Dialogue Summarization",
author = "Zhou, Weixiao and
Li, Gengyao and
Cheng, Xianfu and
Liang, Xinnian and
Zhu, Junnan and
Zhai, Feifei and
Li, Zhoujun",
editor = "Bouamor, Houda and
Pino, Juan and
Bali, Kalika",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2023",
month = dec,
year = "2023",
address = "Singapore",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.findings-emnlp.460/",
doi = "10.18653/v1/2023.findings-emnlp.460",
pages = "6893--6908",
abstract = "Dialogue summarization involves a wide range of scenarios and domains. However, existing methods generally only apply to specific scenarios or domains. In this study, we propose a new pre-trained model specifically designed for multi-scenario multi-domain dialogue summarization. It adopts a multi-stage pre-training strategy to reduce the gap between the pre-training objective and fine-tuning objective. Specifically, we first conduct domain-aware pre-training using large-scale multi-scenario multi-domain dialogue data to enhance the adaptability of our pre-trained model. Then, we conduct task-oriented pre-training using large-scale multi-scenario multi-domain {\textquotedblleft}dialogue-summary{\textquotedblright} parallel data annotated by ChatGPT to enhance the dialogue summarization ability of our pre-trained model. Experimental results on three dialogue summarization datasets from different scenarios and domains indicate that our pre-trained model significantly outperforms previous state-of-the-art models in full fine-tuning, zero-shot, and few-shot settings."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhou-etal-2023-multi">
<titleInfo>
<title>Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Weixiao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gengyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xianfu</namePart>
<namePart type="family">Cheng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xinnian</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junnan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Feifei</namePart>
<namePart type="family">Zhai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhoujun</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: EMNLP 2023</title>
</titleInfo>
<name type="personal">
<namePart type="given">Houda</namePart>
<namePart type="family">Bouamor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Juan</namePart>
<namePart type="family">Pino</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalika</namePart>
<namePart type="family">Bali</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Singapore</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Dialogue summarization involves a wide range of scenarios and domains. However, existing methods generally only apply to specific scenarios or domains. In this study, we propose a new pre-trained model specifically designed for multi-scenario multi-domain dialogue summarization. It adopts a multi-stage pre-training strategy to reduce the gap between the pre-training objective and fine-tuning objective. Specifically, we first conduct domain-aware pre-training using large-scale multi-scenario multi-domain dialogue data to enhance the adaptability of our pre-trained model. Then, we conduct task-oriented pre-training using large-scale multi-scenario multi-domain “dialogue-summary” parallel data annotated by ChatGPT to enhance the dialogue summarization ability of our pre-trained model. Experimental results on three dialogue summarization datasets from different scenarios and domains indicate that our pre-trained model significantly outperforms previous state-of-the-art models in full fine-tuning, zero-shot, and few-shot settings.</abstract>
<identifier type="citekey">zhou-etal-2023-multi</identifier>
<identifier type="doi">10.18653/v1/2023.findings-emnlp.460</identifier>
<location>
<url>https://aclanthology.org/2023.findings-emnlp.460/</url>
</location>
<part>
<date>2023-12</date>
<extent unit="page">
<start>6893</start>
<end>6908</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization
%A Zhou, Weixiao
%A Li, Gengyao
%A Cheng, Xianfu
%A Liang, Xinnian
%A Zhu, Junnan
%A Zhai, Feifei
%A Li, Zhoujun
%Y Bouamor, Houda
%Y Pino, Juan
%Y Bali, Kalika
%S Findings of the Association for Computational Linguistics: EMNLP 2023
%D 2023
%8 December
%I Association for Computational Linguistics
%C Singapore
%F zhou-etal-2023-multi
%X Dialogue summarization involves a wide range of scenarios and domains. However, existing methods generally only apply to specific scenarios or domains. In this study, we propose a new pre-trained model specifically designed for multi-scenario multi-domain dialogue summarization. It adopts a multi-stage pre-training strategy to reduce the gap between the pre-training objective and fine-tuning objective. Specifically, we first conduct domain-aware pre-training using large-scale multi-scenario multi-domain dialogue data to enhance the adaptability of our pre-trained model. Then, we conduct task-oriented pre-training using large-scale multi-scenario multi-domain “dialogue-summary” parallel data annotated by ChatGPT to enhance the dialogue summarization ability of our pre-trained model. Experimental results on three dialogue summarization datasets from different scenarios and domains indicate that our pre-trained model significantly outperforms previous state-of-the-art models in full fine-tuning, zero-shot, and few-shot settings.
%R 10.18653/v1/2023.findings-emnlp.460
%U https://aclanthology.org/2023.findings-emnlp.460/
%U https://doi.org/10.18653/v1/2023.findings-emnlp.460
%P 6893-6908
Markdown (Informal)
[Multi-Stage Pre-training Enhanced by ChatGPT for Multi-Scenario Multi-Domain Dialogue Summarization](https://aclanthology.org/2023.findings-emnlp.460/) (Zhou et al., Findings 2023)
ACL