@inproceedings{zeng-etal-2020-meddialog,
title = "{M}ed{D}ialog: Large-scale Medical Dialogue Datasets",
author = "Zeng, Guangtao and
Yang, Wenmian and
Ju, Zeqian and
Yang, Yue and
Wang, Sicheng and
Zhang, Ruisi and
Zhou, Meng and
Zeng, Jiaqi and
Dong, Xiangyu and
Zhang, Ruoyu and
Fang, Hongchao and
Zhu, Penghui and
Chen, Shu and
Xie, Pengtao",
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.743",
doi = "10.18653/v1/2020.emnlp-main.743",
pages = "9241--9250",
abstract = "Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build large-scale medical dialogue datasets {--} MedDialog, which contain 1) a Chinese dataset with 3.4 million conversations between patients and doctors, 11.3 million utterances, 660.2 million tokens, covering 172 specialties of diseases, and 2) an English dataset with 0.26 million conversations, 0.51 million utterances, 44.53 million tokens, covering 96 specialties of diseases. To our best knowledge, MedDialog is the largest medical dialogue dataset to date. We pretrain several dialogue generation models on the Chinese MedDialog dataset, including Transformer, GPT, BERT-GPT, and compare their performance. It is shown that models trained on MedDialog are able to generate clinically correct and doctor-like medical dialogues. We also study the transferability of models trained on MedDialog to low-resource medical dialogue generation tasks. It is shown that via transfer learning which finetunes the models pretrained on MedDialog, the performance on medical dialogue generation tasks with small datasets can be greatly improved, as shown in human evaluation and automatic evaluation. The datasets and code are available at https://github.com/UCSD-AI4H/Medical-Dialogue-System",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zeng-etal-2020-meddialog">
<titleInfo>
<title>MedDialog: Large-scale Medical Dialogue Datasets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Guangtao</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wenmian</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zeqian</namePart>
<namePart type="family">Ju</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sicheng</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruisi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Meng</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaqi</namePart>
<namePart type="family">Zeng</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiangyu</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruoyu</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hongchao</namePart>
<namePart type="family">Fang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Penghui</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Pengtao</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-nov</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>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build large-scale medical dialogue datasets – MedDialog, which contain 1) a Chinese dataset with 3.4 million conversations between patients and doctors, 11.3 million utterances, 660.2 million tokens, covering 172 specialties of diseases, and 2) an English dataset with 0.26 million conversations, 0.51 million utterances, 44.53 million tokens, covering 96 specialties of diseases. To our best knowledge, MedDialog is the largest medical dialogue dataset to date. We pretrain several dialogue generation models on the Chinese MedDialog dataset, including Transformer, GPT, BERT-GPT, and compare their performance. It is shown that models trained on MedDialog are able to generate clinically correct and doctor-like medical dialogues. We also study the transferability of models trained on MedDialog to low-resource medical dialogue generation tasks. It is shown that via transfer learning which finetunes the models pretrained on MedDialog, the performance on medical dialogue generation tasks with small datasets can be greatly improved, as shown in human evaluation and automatic evaluation. The datasets and code are available at https://github.com/UCSD-AI4H/Medical-Dialogue-System</abstract>
<identifier type="citekey">zeng-etal-2020-meddialog</identifier>
<identifier type="doi">10.18653/v1/2020.emnlp-main.743</identifier>
<location>
<url>https://aclanthology.org/2020.emnlp-main.743</url>
</location>
<part>
<date>2020-nov</date>
<extent unit="page">
<start>9241</start>
<end>9250</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MedDialog: Large-scale Medical Dialogue Datasets
%A Zeng, Guangtao
%A Yang, Wenmian
%A Ju, Zeqian
%A Yang, Yue
%A Wang, Sicheng
%A Zhang, Ruisi
%A Zhou, Meng
%A Zeng, Jiaqi
%A Dong, Xiangyu
%A Zhang, Ruoyu
%A Fang, Hongchao
%A Zhu, Penghui
%A Chen, Shu
%A Xie, Pengtao
%S Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
%D 2020
%8 nov
%I Association for Computational Linguistics
%C Online
%F zeng-etal-2020-meddialog
%X Medical dialogue systems are promising in assisting in telemedicine to increase access to healthcare services, improve the quality of patient care, and reduce medical costs. To facilitate the research and development of medical dialogue systems, we build large-scale medical dialogue datasets – MedDialog, which contain 1) a Chinese dataset with 3.4 million conversations between patients and doctors, 11.3 million utterances, 660.2 million tokens, covering 172 specialties of diseases, and 2) an English dataset with 0.26 million conversations, 0.51 million utterances, 44.53 million tokens, covering 96 specialties of diseases. To our best knowledge, MedDialog is the largest medical dialogue dataset to date. We pretrain several dialogue generation models on the Chinese MedDialog dataset, including Transformer, GPT, BERT-GPT, and compare their performance. It is shown that models trained on MedDialog are able to generate clinically correct and doctor-like medical dialogues. We also study the transferability of models trained on MedDialog to low-resource medical dialogue generation tasks. It is shown that via transfer learning which finetunes the models pretrained on MedDialog, the performance on medical dialogue generation tasks with small datasets can be greatly improved, as shown in human evaluation and automatic evaluation. The datasets and code are available at https://github.com/UCSD-AI4H/Medical-Dialogue-System
%R 10.18653/v1/2020.emnlp-main.743
%U https://aclanthology.org/2020.emnlp-main.743
%U https://doi.org/10.18653/v1/2020.emnlp-main.743
%P 9241-9250
Markdown (Informal)
[MedDialog: Large-scale Medical Dialogue Datasets](https://aclanthology.org/2020.emnlp-main.743) (Zeng et al., EMNLP 2020)
ACL
- Guangtao Zeng, Wenmian Yang, Zeqian Ju, Yue Yang, Sicheng Wang, Ruisi Zhang, Meng Zhou, Jiaqi Zeng, Xiangyu Dong, Ruoyu Zhang, Hongchao Fang, Penghui Zhu, Shu Chen, and Pengtao Xie. 2020. MedDialog: Large-scale Medical Dialogue Datasets. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 9241–9250, Online. Association for Computational Linguistics.