no code implementations • 18 Dec 2023 • Akshay Batheja, Sourabh Deoghare, Diptesh Kanojia, Pushpak Bhattacharyya
We propose a repair-filter-use methodology that uses an APE system to correct errors on the target side of the MT training data.
no code implementations • 6 Jun 2023 • Akshay Batheja, Pushpak Bhattacharyya
To the best of our knowledge, this is a novel adaptation of the QE framework to extract quality parallel corpus from the pseudo-parallel corpus.
no code implementations • 21 May 2023 • Shivam Mhaskar, Vineet Bhat, Akshay Batheja, Sourabh Deoghare, Paramveer Choudhary, Pushpak Bhattacharyya
In this work, we present our deployment-ready Speech-to-Speech Machine Translation (SSMT) system for English-Hindi, English-Marathi, and Hindi-Marathi language pairs.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +5
no code implementations • 19 Jan 2023 • Akshay Batheja, Pushpak Bhattacharyya
In this paper, we show that the combination of Phrase Pair Injection and Corpus Filtering boosts the performance of Neural Machine Translation (NMT) systems.