Robust Prediction of Punctuation and Truecasing for Medical ASR

Monica Sunkara, Srikanth Ronanki, Kalpit Dixit, Sravan Bodapati, Katrin Kirchhoff


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.
Anthology ID:
2020.nlpmc-1.8
Volume:
Proceedings of the First Workshop on Natural Language Processing for Medical Conversations
Month:
July
Year:
2020
Address:
Online
Editors:
Parminder Bhatia, Steven Lin, Rashmi Gangadharaiah, Byron Wallace, Izhak Shafran, Chaitanya Shivade, Nan Du, Mona Diab
Venue:
NLPMC
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
53–62
Language:
URL:
https://aclanthology.org/2020.nlpmc-1.8
DOI:
10.18653/v1/2020.nlpmc-1.8
Bibkey:
Cite (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.
Cite (Informal):
Robust Prediction of Punctuation and Truecasing for Medical ASR (Sunkara et al., NLPMC 2020)
Copy Citation:
PDF:
https://aclanthology.org/2020.nlpmc-1.8.pdf
Video:
 http://slideslive.com/38929891