8 citations · 9 across the 2 of their papers we have counts for
3 papers
Character-based NMT with Transformer
Rohit Gupta, Laurent Besacier, Marc Dymetman +1
Character-based translation has several appealing advantages, but its performance is in general worse than a carefully tuned BPE baseline. In this paper we study the impact of char…
Improving Robustness in Real-World Neural Machine Translation Engines
Rohit Gupta, Patrik Lambert, Raj Nath Patel +1
As a commercial provider of machine translation, we are constantly training engines for a variety of uses, languages, and content types. In each case, there can be many variables,…
ParsRec: A Novel Meta-Learning Approach to Recommending Bibliographic Reference Parsers
Dominika Tkaczyk, Rohit Gupta, Riccardo Cinti +1
Bibliographic reference parsers extract machine-readable metadata such as author names, title, journal, and year from bibliographic reference strings. To extract the metadata, the…