@inproceedings{chintagunta-etal-2021-medically,
title = "Medically Aware {GPT}-3 as a Data Generator for Medical Dialogue Summarization",
author = "Chintagunta, Bharath and
Katariya, Namit and
Amatriain, Xavier and
Kannan, Anitha",
editor = "Shivade, Chaitanya and
Gangadharaiah, Rashmi and
Gella, Spandana and
Konam, Sandeep and
Yuan, Shaoqing and
Zhang, Yi and
Bhatia, Parminder and
Wallace, Byron",
booktitle = "Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.nlpmc-1.9",
doi = "10.18653/v1/2021.nlpmc-1.9",
pages = "66--76",
abstract = "In medical dialogue summarization, summaries must be coherent and must capture all the medically relevant information in the dialogue. However, learning effective models for summarization require large amounts of labeled data which is especially hard to obtain. We present an algorithm to create synthetic training data with an explicit focus on capturing medically relevant information. We utilize GPT-3 as the backbone of our algorithm and scale 210 human labeled examples to yield results comparable to using 6400 human labeled examples ({\textasciitilde}30x) leveraging low-shot learning and an ensemble method. In detailed experiments, we show that this approach produces high quality training data that can further be combined with human labeled data to get summaries that are strongly preferable to those produced by models trained on human data alone both in terms of medical accuracy and coherency.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="chintagunta-etal-2021-medically">
<titleInfo>
<title>Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharath</namePart>
<namePart type="family">Chintagunta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Namit</namePart>
<namePart type="family">Katariya</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xavier</namePart>
<namePart type="family">Amatriain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anitha</namePart>
<namePart type="family">Kannan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chaitanya</namePart>
<namePart type="family">Shivade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rashmi</namePart>
<namePart type="family">Gangadharaiah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Spandana</namePart>
<namePart type="family">Gella</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sandeep</namePart>
<namePart type="family">Konam</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shaoqing</namePart>
<namePart type="family">Yuan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parminder</namePart>
<namePart type="family">Bhatia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Byron</namePart>
<namePart type="family">Wallace</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>In medical dialogue summarization, summaries must be coherent and must capture all the medically relevant information in the dialogue. However, learning effective models for summarization require large amounts of labeled data which is especially hard to obtain. We present an algorithm to create synthetic training data with an explicit focus on capturing medically relevant information. We utilize GPT-3 as the backbone of our algorithm and scale 210 human labeled examples to yield results comparable to using 6400 human labeled examples (~30x) leveraging low-shot learning and an ensemble method. In detailed experiments, we show that this approach produces high quality training data that can further be combined with human labeled data to get summaries that are strongly preferable to those produced by models trained on human data alone both in terms of medical accuracy and coherency.</abstract>
<identifier type="citekey">chintagunta-etal-2021-medically</identifier>
<identifier type="doi">10.18653/v1/2021.nlpmc-1.9</identifier>
<location>
<url>https://aclanthology.org/2021.nlpmc-1.9</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>66</start>
<end>76</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization
%A Chintagunta, Bharath
%A Katariya, Namit
%A Amatriain, Xavier
%A Kannan, Anitha
%Y Shivade, Chaitanya
%Y Gangadharaiah, Rashmi
%Y Gella, Spandana
%Y Konam, Sandeep
%Y Yuan, Shaoqing
%Y Zhang, Yi
%Y Bhatia, Parminder
%Y Wallace, Byron
%S Proceedings of the Second Workshop on Natural Language Processing for Medical Conversations
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F chintagunta-etal-2021-medically
%X In medical dialogue summarization, summaries must be coherent and must capture all the medically relevant information in the dialogue. However, learning effective models for summarization require large amounts of labeled data which is especially hard to obtain. We present an algorithm to create synthetic training data with an explicit focus on capturing medically relevant information. We utilize GPT-3 as the backbone of our algorithm and scale 210 human labeled examples to yield results comparable to using 6400 human labeled examples (~30x) leveraging low-shot learning and an ensemble method. In detailed experiments, we show that this approach produces high quality training data that can further be combined with human labeled data to get summaries that are strongly preferable to those produced by models trained on human data alone both in terms of medical accuracy and coherency.
%R 10.18653/v1/2021.nlpmc-1.9
%U https://aclanthology.org/2021.nlpmc-1.9
%U https://doi.org/10.18653/v1/2021.nlpmc-1.9
%P 66-76
Markdown (Informal)
[Medically Aware GPT-3 as a Data Generator for Medical Dialogue Summarization](https://aclanthology.org/2021.nlpmc-1.9) (Chintagunta et al., NLPMC 2021)
ACL