@inproceedings{singh-etal-2023-large,
title = "Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor Conversations",
author = "Singh, Gagandeep and
Pan, Yue and
Andres-Ferrer, Jesus and
Del-Agua, Miguel and
Diehl, Frank and
Pinto, Joel and
Vozila, Paul",
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-1.18",
doi = "10.18653/v1/2023.clinicalnlp-1.18",
pages = "138--143",
abstract = "We present our work on building large scale sequence-to-sequence models for generating clinical note from patient-doctor conversation. This is formulated as an abstractive summarization task for which we use encoder-decoder transformer model with pointer-generator. We discuss various modeling enhancements to this baseline model which include using subword and multiword tokenization scheme, prefixing the targets with a chain-of-clinical-facts, and training with contrastive loss that is defined over various candidate summaries. We also use flash attention during training and query chunked attention during inference to be able to process long input and output sequences and to improve computational efficiency. Experiments are conducted on a dataset containing about 900K encounters from around 1800 healthcare providers covering 27 specialties. The results are broken down into primary care and non-primary care specialties. Consistent accuracy improvements are observed across both of these categories.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="singh-etal-2023-large">
<titleInfo>
<title>Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Gagandeep</namePart>
<namePart type="family">Singh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jesus</namePart>
<namePart type="family">Andres-Ferrer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Miguel</namePart>
<namePart type="family">Del-Agua</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frank</namePart>
<namePart type="family">Diehl</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joel</namePart>
<namePart type="family">Pinto</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Vozila</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>We present our work on building large scale sequence-to-sequence models for generating clinical note from patient-doctor conversation. This is formulated as an abstractive summarization task for which we use encoder-decoder transformer model with pointer-generator. We discuss various modeling enhancements to this baseline model which include using subword and multiword tokenization scheme, prefixing the targets with a chain-of-clinical-facts, and training with contrastive loss that is defined over various candidate summaries. We also use flash attention during training and query chunked attention during inference to be able to process long input and output sequences and to improve computational efficiency. Experiments are conducted on a dataset containing about 900K encounters from around 1800 healthcare providers covering 27 specialties. The results are broken down into primary care and non-primary care specialties. Consistent accuracy improvements are observed across both of these categories.</abstract>
<identifier type="citekey">singh-etal-2023-large</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.18</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.18</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>138</start>
<end>143</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor Conversations
%A Singh, Gagandeep
%A Pan, Yue
%A Andres-Ferrer, Jesus
%A Del-Agua, Miguel
%A Diehl, Frank
%A Pinto, Joel
%A Vozila, Paul
%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 singh-etal-2023-large
%X We present our work on building large scale sequence-to-sequence models for generating clinical note from patient-doctor conversation. This is formulated as an abstractive summarization task for which we use encoder-decoder transformer model with pointer-generator. We discuss various modeling enhancements to this baseline model which include using subword and multiword tokenization scheme, prefixing the targets with a chain-of-clinical-facts, and training with contrastive loss that is defined over various candidate summaries. We also use flash attention during training and query chunked attention during inference to be able to process long input and output sequences and to improve computational efficiency. Experiments are conducted on a dataset containing about 900K encounters from around 1800 healthcare providers covering 27 specialties. The results are broken down into primary care and non-primary care specialties. Consistent accuracy improvements are observed across both of these categories.
%R 10.18653/v1/2023.clinicalnlp-1.18
%U https://aclanthology.org/2023.clinicalnlp-1.18
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.18
%P 138-143
Markdown (Informal)
[Large Scale Sequence-to-Sequence Models for Clinical Note Generation from Patient-Doctor Conversations](https://aclanthology.org/2023.clinicalnlp-1.18) (Singh et al., ClinicalNLP 2023)
ACL