Disfluency Correction using Unsupervised and Semi-supervised Learning

Nikhil Saini, Drumil Trivedi, Shreya Khare, Tejas Dhamecha, Preethi Jyothi, Samarth Bharadwaj, Pushpak Bhattacharyya

Abstract
Spoken language is different from the written language in its style and structure. Disfluencies that appear in transcriptions from speech recognition systems generally hamper the performance of downstream NLP tasks. Thus, a disfluency correction system that converts disfluent to fluent text is of great value. This paper introduces a disfluency correction model that translates disfluent to fluent text by drawing inspiration from recent encoder-decoder unsupervised style-transfer models for text. We also show considerable benefits in performance when utilizing a small sample of 500 parallel disfluent-fluent sentences in a semi-supervised way. Our unsupervised approach achieves a BLEU score of 79.39 on the Switchboard corpus test set, with further improvement to a BLEU score of 85.28 with semi-supervision. Both are comparable to two competitive fully-supervised models.
Anthology ID:
2021.eacl-main.299
Volume:
Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume
Month:
April
Year:
2021
Address:
Online
Editors:
Paola Merlo, Jorg Tiedemann, Reut Tsarfaty
Venue:
EACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
3421–3427
Language:
URL:
https://aclanthology.org/2021.eacl-main.299
DOI:
10.18653/v1/2021.eacl-main.299
Bibkey:
Cite (ACL):
Nikhil Saini, Drumil Trivedi, Shreya Khare, Tejas Dhamecha, Preethi Jyothi, Samarth Bharadwaj, and Pushpak Bhattacharyya. 2021. Disfluency Correction using Unsupervised and Semi-supervised Learning. In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Main Volume, pages 3421–3427, Online. Association for Computational Linguistics.
Cite (Informal):
Disfluency Correction using Unsupervised and Semi-supervised Learning (Saini et al., EACL 2021)
Copy Citation:
PDF:
https://preview.aclanthology.org/nschneid-patch-1/2021.eacl-main.299.pdf
PDF Search