@inproceedings{sunkara-etal-2020-robust,
title = "Robust Prediction of Punctuation and Truecasing for Medical {ASR}",
author = "Sunkara, Monica and
Ronanki, Srikanth and
Dixit, Kalpit and
Bodapati, Sravan and
Kirchhoff, Katrin",
editor = "Bhatia, Parminder and
Lin, Steven and
Gangadharaiah, Rashmi and
Wallace, Byron and
Shafran, Izhak and
Shivade, Chaitanya and
Du, Nan and
Diab, Mona",
booktitle = "Proceedings of the First Workshop on Natural Language Processing for Medical Conversations",
month = jul,
year = "2020",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2020.nlpmc-1.8",
doi = "10.18653/v1/2020.nlpmc-1.8",
pages = "53--62",
abstract = "Automatic speech recognition (ASR) systems in the medical domain that focus on transcribing clinical dictations and doctor-patient conversations often pose many challenges due to the complexity of the domain. ASR output typically undergoes automatic punctuation to enable users to speak naturally, without having to vocalize awkward and explicit punctuation commands, such as {``}period{''}, {``}add comma{''} or {``}exclamation point{''}, while truecasing enhances user readability and improves the performance of downstream NLP tasks. This paper proposes a conditional joint modeling framework for prediction of punctuation and truecasing using pretrained masked language models such as BERT, BioBERT and RoBERTa. We also present techniques for domain and task specific adaptation by fine-tuning masked language models with medical domain data. Finally, we improve the robustness of the model against common errors made in ASR by performing data augmentation. Experiments performed on dictation and conversational style corpora show that our proposed model achieves 5{\%} absolute improvement on ground truth text and 10{\%} improvement on ASR outputs over baseline models under F1 metric.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sunkara-etal-2020-robust">
<titleInfo>
<title>Robust Prediction of Punctuation and Truecasing for Medical ASR</title>
</titleInfo>
<name type="personal">
<namePart type="given">Monica</namePart>
<namePart type="family">Sunkara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Srikanth</namePart>
<namePart type="family">Ronanki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kalpit</namePart>
<namePart type="family">Dixit</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sravan</namePart>
<namePart type="family">Bodapati</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Katrin</namePart>
<namePart type="family">Kirchhoff</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2020-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Natural Language Processing for Medical Conversations</title>
</titleInfo>
<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">Steven</namePart>
<namePart type="family">Lin</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">Byron</namePart>
<namePart type="family">Wallace</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Izhak</namePart>
<namePart type="family">Shafran</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<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">Nan</namePart>
<namePart type="family">Du</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mona</namePart>
<namePart type="family">Diab</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>Automatic speech recognition (ASR) systems in the medical domain that focus on transcribing clinical dictations and doctor-patient conversations often pose many challenges due to the complexity of the domain. ASR output typically undergoes automatic punctuation to enable users to speak naturally, without having to vocalize awkward and explicit punctuation commands, such as “period”, “add comma” or “exclamation point”, while truecasing enhances user readability and improves the performance of downstream NLP tasks. This paper proposes a conditional joint modeling framework for prediction of punctuation and truecasing using pretrained masked language models such as BERT, BioBERT and RoBERTa. We also present techniques for domain and task specific adaptation by fine-tuning masked language models with medical domain data. Finally, we improve the robustness of the model against common errors made in ASR by performing data augmentation. Experiments performed on dictation and conversational style corpora show that our proposed model achieves 5% absolute improvement on ground truth text and 10% improvement on ASR outputs over baseline models under F1 metric.</abstract>
<identifier type="citekey">sunkara-etal-2020-robust</identifier>
<identifier type="doi">10.18653/v1/2020.nlpmc-1.8</identifier>
<location>
<url>https://aclanthology.org/2020.nlpmc-1.8</url>
</location>
<part>
<date>2020-07</date>
<extent unit="page">
<start>53</start>
<end>62</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Robust Prediction of Punctuation and Truecasing for Medical ASR
%A Sunkara, Monica
%A Ronanki, Srikanth
%A Dixit, Kalpit
%A Bodapati, Sravan
%A Kirchhoff, Katrin
%Y Bhatia, Parminder
%Y Lin, Steven
%Y Gangadharaiah, Rashmi
%Y Wallace, Byron
%Y Shafran, Izhak
%Y Shivade, Chaitanya
%Y Du, Nan
%Y Diab, Mona
%S Proceedings of the First Workshop on Natural Language Processing for Medical Conversations
%D 2020
%8 July
%I Association for Computational Linguistics
%C Online
%F sunkara-etal-2020-robust
%X Automatic speech recognition (ASR) systems in the medical domain that focus on transcribing clinical dictations and doctor-patient conversations often pose many challenges due to the complexity of the domain. ASR output typically undergoes automatic punctuation to enable users to speak naturally, without having to vocalize awkward and explicit punctuation commands, such as “period”, “add comma” or “exclamation point”, while truecasing enhances user readability and improves the performance of downstream NLP tasks. This paper proposes a conditional joint modeling framework for prediction of punctuation and truecasing using pretrained masked language models such as BERT, BioBERT and RoBERTa. We also present techniques for domain and task specific adaptation by fine-tuning masked language models with medical domain data. Finally, we improve the robustness of the model against common errors made in ASR by performing data augmentation. Experiments performed on dictation and conversational style corpora show that our proposed model achieves 5% absolute improvement on ground truth text and 10% improvement on ASR outputs over baseline models under F1 metric.
%R 10.18653/v1/2020.nlpmc-1.8
%U https://aclanthology.org/2020.nlpmc-1.8
%U https://doi.org/10.18653/v1/2020.nlpmc-1.8
%P 53-62
Markdown (Informal)
[Robust Prediction of Punctuation and Truecasing for Medical ASR](https://aclanthology.org/2020.nlpmc-1.8) (Sunkara et al., NLPMC 2020)
ACL
- Monica Sunkara, Srikanth Ronanki, Kalpit Dixit, Sravan Bodapati, and Katrin Kirchhoff. 2020. Robust Prediction of Punctuation and Truecasing for Medical ASR. In Proceedings of the First Workshop on Natural Language Processing for Medical Conversations, pages 53–62, Online. Association for Computational Linguistics.