@inproceedings{min-etal-2023-navigating,
title = "Navigating Data Scarcity: Pretraining for Medical Utterance Classification",
author = "Min, Do June and
Perez-Rosas, Veronica and
Mihalcea, Rada",
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-1.8",
doi = "10.18653/v1/2023.clinicalnlp-1.8",
pages = "59--68",
abstract = "Pretrained language models leverage self-supervised learning to use large amounts of unlabeled text for learning contextual representations of sequences. However, in the domain of medical conversations, the availability of large, public datasets is limited due to issues of privacy and data management. In this paper, we study the effectiveness of dialog-aware pretraining objectives and multiphase training in using unlabeled data to improve LMs training for medical utterance classification. The objectives of pretraining for dialog awareness involve tasks that take into account the structure of conversations, including features such as turn-taking and the roles of speakers. The multiphase training process uses unannotated data in a sequence that prioritizes similarities and connections between different domains. We empirically evaluate these methods on conversational dialog classification tasks in the medical and counseling domains, and find that multiphase training can help achieve higher performance than standard pretraining or finetuning.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="min-etal-2023-navigating">
<titleInfo>
<title>Navigating Data Scarcity: Pretraining for Medical Utterance Classification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Do</namePart>
<namePart type="given">June</namePart>
<namePart type="family">Min</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronica</namePart>
<namePart type="family">Perez-Rosas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rada</namePart>
<namePart type="family">Mihalcea</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>Pretrained language models leverage self-supervised learning to use large amounts of unlabeled text for learning contextual representations of sequences. However, in the domain of medical conversations, the availability of large, public datasets is limited due to issues of privacy and data management. In this paper, we study the effectiveness of dialog-aware pretraining objectives and multiphase training in using unlabeled data to improve LMs training for medical utterance classification. The objectives of pretraining for dialog awareness involve tasks that take into account the structure of conversations, including features such as turn-taking and the roles of speakers. The multiphase training process uses unannotated data in a sequence that prioritizes similarities and connections between different domains. We empirically evaluate these methods on conversational dialog classification tasks in the medical and counseling domains, and find that multiphase training can help achieve higher performance than standard pretraining or finetuning.</abstract>
<identifier type="citekey">min-etal-2023-navigating</identifier>
<identifier type="doi">10.18653/v1/2023.clinicalnlp-1.8</identifier>
<location>
<url>https://aclanthology.org/2023.clinicalnlp-1.8</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>59</start>
<end>68</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Navigating Data Scarcity: Pretraining for Medical Utterance Classification
%A Min, Do June
%A Perez-Rosas, Veronica
%A Mihalcea, Rada
%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 min-etal-2023-navigating
%X Pretrained language models leverage self-supervised learning to use large amounts of unlabeled text for learning contextual representations of sequences. However, in the domain of medical conversations, the availability of large, public datasets is limited due to issues of privacy and data management. In this paper, we study the effectiveness of dialog-aware pretraining objectives and multiphase training in using unlabeled data to improve LMs training for medical utterance classification. The objectives of pretraining for dialog awareness involve tasks that take into account the structure of conversations, including features such as turn-taking and the roles of speakers. The multiphase training process uses unannotated data in a sequence that prioritizes similarities and connections between different domains. We empirically evaluate these methods on conversational dialog classification tasks in the medical and counseling domains, and find that multiphase training can help achieve higher performance than standard pretraining or finetuning.
%R 10.18653/v1/2023.clinicalnlp-1.8
%U https://aclanthology.org/2023.clinicalnlp-1.8
%U https://doi.org/10.18653/v1/2023.clinicalnlp-1.8
%P 59-68
Markdown (Informal)
[Navigating Data Scarcity: Pretraining for Medical Utterance Classification](https://aclanthology.org/2023.clinicalnlp-1.8) (Min et al., ClinicalNLP 2023)
ACL