no code implementations • NAACL 2022 • Proyag Pal, Kenneth Heafield
This paper describes a method to quantify the amount of information H(t|s) added by the target sentence t that is not present in the source s in a neural machine translation system.
1 code implementation • WMT (EMNLP) 2021 • Proyag Pal, Alham Fikri Aji, Pinzhen Chen, Sukanta Sen
We describe the University of Edinburgh’s Bengali\leftrightarrowHindi constrained systems submitted to the WMT21 News Translation task.
no code implementations • 22 May 2023 • Proyag Pal, Brian Thompson, Yogesh Virkar, Prashant Mathur, Alexandra Chronopoulou, Marcello Federico
To translate speech for automatic dubbing, machine translation needs to be isochronous, i. e. translated speech needs to be aligned with the source in terms of speech durations.