@inproceedings{feng-etal-2021-language,
title = "Language Model as an Annotator: Exploring {D}ialo{GPT} for Dialogue Summarization",
author = "Feng, Xiachong and
Feng, Xiaocheng and
Qin, Libo and
Qin, Bing and
Liu, Ting",
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 1: Long Papers)",
month = aug,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.acl-long.117",
doi = "10.18653/v1/2021.acl-long.117",
pages = "1479--1491",
abstract = "Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain toolkits that are dialog-agnostic or heavily relied on human annotations. In this paper, we show how DialoGPT, a pre-trained model for conversational response generation, can be developed as an unsupervised dialogue annotator, which takes advantage of dialogue background knowledge encoded in DialoGPT. We apply DialoGPT to label three types of features on two dialogue summarization datasets, SAMSum and AMI, and employ pre-trained and non pre-trained models as our summarizers. Experimental results show that our proposed method can obtain remarkable improvements on both datasets and achieves new state-of-the-art performance on the SAMSum dataset.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="feng-etal-2021-language">
<titleInfo>
<title>Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiachong</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaocheng</namePart>
<namePart type="family">Feng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Libo</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Qin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ting</namePart>
<namePart type="family">Liu</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 1: Long 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>Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain toolkits that are dialog-agnostic or heavily relied on human annotations. In this paper, we show how DialoGPT, a pre-trained model for conversational response generation, can be developed as an unsupervised dialogue annotator, which takes advantage of dialogue background knowledge encoded in DialoGPT. We apply DialoGPT to label three types of features on two dialogue summarization datasets, SAMSum and AMI, and employ pre-trained and non pre-trained models as our summarizers. Experimental results show that our proposed method can obtain remarkable improvements on both datasets and achieves new state-of-the-art performance on the SAMSum dataset.</abstract>
<identifier type="citekey">feng-etal-2021-language</identifier>
<identifier type="doi">10.18653/v1/2021.acl-long.117</identifier>
<location>
<url>https://aclanthology.org/2021.acl-long.117</url>
</location>
<part>
<date>2021-08</date>
<extent unit="page">
<start>1479</start>
<end>1491</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization
%A Feng, Xiachong
%A Feng, Xiaocheng
%A Qin, Libo
%A Qin, Bing
%A Liu, Ting
%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 1: Long Papers)
%D 2021
%8 August
%I Association for Computational Linguistics
%C Online
%F feng-etal-2021-language
%X Current dialogue summarization systems usually encode the text with a number of general semantic features (e.g., keywords and topics) to gain more powerful dialogue modeling capabilities. However, these features are obtained via open-domain toolkits that are dialog-agnostic or heavily relied on human annotations. In this paper, we show how DialoGPT, a pre-trained model for conversational response generation, can be developed as an unsupervised dialogue annotator, which takes advantage of dialogue background knowledge encoded in DialoGPT. We apply DialoGPT to label three types of features on two dialogue summarization datasets, SAMSum and AMI, and employ pre-trained and non pre-trained models as our summarizers. Experimental results show that our proposed method can obtain remarkable improvements on both datasets and achieves new state-of-the-art performance on the SAMSum dataset.
%R 10.18653/v1/2021.acl-long.117
%U https://aclanthology.org/2021.acl-long.117
%U https://doi.org/10.18653/v1/2021.acl-long.117
%P 1479-1491
Markdown (Informal)
[Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization](https://aclanthology.org/2021.acl-long.117) (Feng et al., ACL-IJCNLP 2021)
ACL
- Xiachong Feng, Xiaocheng Feng, Libo Qin, Bing Qin, and Ting Liu. 2021. Language Model as an Annotator: Exploring DialoGPT for Dialogue Summarization. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 1479–1491, Online. Association for Computational Linguistics.