@inproceedings{tang-etal-2023-aligning,
title = "Aligning Factual Consistency for Clinical Studies Summarization through Reinforcement Learning",
author = "Tang, Xiangru and
Cohan, Arman and
Gerstein, Mark",
editor = "Naumann, Tristan and
Ben Abacha, Asma and
Bethard, Steven and
Roberts, Kirk and
Rumshisky, Anna",
booktitle = "Proceedings of the 5th Clinical Natural Language Processing Workshop",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.clinicalnlp-1.7",
doi = "10.18653/v1/2023.clinicalnlp-1.7",
pages = "48--58",
abstract = "In the rapidly evolving landscape of medical research, accurate and concise summarization of clinical studies is crucial to support evidence-based practice. This paper presents a novel approach to clinical studies summarization, leveraging reinforcement learning to enhance factual consistency and align with human annotator preferences. Our work focuses on two tasks: Conclusion Generation and Review Generation. We train a CONFIT summarization model that outperforms GPT-3 and previous state-of-the-art models on the same datasets and collects expert and crowd-worker annotations to evaluate the quality and factual consistency of the generated summaries. These annotations enable us to measure the correlation of various automatic metrics, including modern factual evaluation metrics like QAFactEval, with human-assessed factual consistency. By employing top-correlated metrics as objectives for a reinforcement learning model, we demonstrate improved factuality in generated summaries that are preferred by human annotators.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="tang-etal-2023-aligning">
<titleInfo>
<title>Aligning Factual Consistency for Clinical Studies Summarization through Reinforcement Learning</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xiangru</namePart>
<namePart type="family">Tang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arman</namePart>
<namePart type="family">Cohan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mark</namePart>
<namePart type="family">Gerstein</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th Clinical Natural Language Processing Workshop</title>
</titleInfo>
<name type="personal">
<namePart type="given">Tristan</namePart>
<namePart type="family">Naumann</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Asma</namePart>
<namePart type="family">Ben Abacha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the rapidly evolving landscape of medical research, accurate and concise summarization of clinical studies is crucial to support evidence-based practice. This paper presents a novel approach to clinical studies summarization, leveraging reinforcement learning to enhance factual consistency and align with human annotator preferences. Our work focuses on two tasks: Conclusion Generation and Review Generation. We train a CONFIT summarization model that outperforms GPT-3 and previous state-of-the-art models on the same datasets and collects expert and crowd-worker annotations to evaluate the quality and factual consistency of the generated summaries. These annotations enable us to measure the correlation of various automatic metrics, including modern factual evaluation metrics like QAFactEval, with human-assessed factual consistency. By employing top-correlated metrics as objectives for a reinforcement learning model, we demonstrate improved factuality in generated summaries that are preferred by human annotators.</abstract>
<identifier type="citekey">tang-etal-2023-aligning</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.7</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.7</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>48</start>
<end>58</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Aligning Factual Consistency for Clinical Studies Summarization through Reinforcement Learning
%A Tang, Xiangru
%A Cohan, Arman
%A Gerstein, Mark
%Y Naumann, Tristan
%Y Ben Abacha, Asma
%Y Bethard, Steven
%Y Roberts, Kirk
%Y Rumshisky, Anna
%S Proceedings of the 5th Clinical Natural Language Processing Workshop
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F tang-etal-2023-aligning
%X In the rapidly evolving landscape of medical research, accurate and concise summarization of clinical studies is crucial to support evidence-based practice. This paper presents a novel approach to clinical studies summarization, leveraging reinforcement learning to enhance factual consistency and align with human annotator preferences. Our work focuses on two tasks: Conclusion Generation and Review Generation. We train a CONFIT summarization model that outperforms GPT-3 and previous state-of-the-art models on the same datasets and collects expert and crowd-worker annotations to evaluate the quality and factual consistency of the generated summaries. These annotations enable us to measure the correlation of various automatic metrics, including modern factual evaluation metrics like QAFactEval, with human-assessed factual consistency. By employing top-correlated metrics as objectives for a reinforcement learning model, we demonstrate improved factuality in generated summaries that are preferred by human annotators.
%R 10.18653/v1/2023.clinicalnlp-1.7
%U https://aclanthology.org/2023.clinicalnlp-1.7
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.7
%P 48-58
Markdown (Informal)
[Aligning Factual Consistency for Clinical Studies Summarization through Reinforcement Learning](https://aclanthology.org/2023.clinicalnlp-1.7) (Tang et al., ClinicalNLP 2023)
ACL