Papers by Shreya Khare
Disfluency Correction using Unsupervised and Semi-supervised Learning (2021.eacl-main)
Copied to clipboard
Nikhil Saini, Drumil Trivedi, Shreya Khare, Tejas Dhamecha, Preethi Jyothi, Samarth Bharadwaj, Pushpak Bhattacharyya
| Challenge: | Disfluencies in conversational speech can affect performance of downstream NLP tasks. |
| Approach: | They propose a disfluency correction model that converts disfluent to fluent text . they use unsupervised encoder-decoder models to generate semi-supervised models . |
| Outcome: | The proposed model achieves a BLEU score of 79.39 on the Switchboard corpus test set and 85.28 with semi-supervision. |