Multilingual models are often particularly dependent on scaling to gener...
JoeyS2T is a JoeyNMT extension for speech-to-text tasks such as automati...
In this paper we share findings from our effort to build practical machi...
Non-autoregressive (NAR) machine translation has recently achieved
signi...
Training data for machine translation (MT) is often sourced from a multi...
A "bigger is better" explosion in the number of parameters in deep neura...
Despite the increasing number of large and comprehensive machine transla...
While achieving state-of-the-art results in multiple tasks and languages...
Policy gradient algorithms have found wide adoption in NLP, but have rec...
With the success of large-scale pre-training and multilingual modeling i...
We take a step towards addressing the under-representation of the Africa...
Low-resource languages present unique challenges to (neural) machine
tra...
Large volumes of interaction logs can be collected from NLP systems that...
Recent progress in text classification has been focused on high-resource...
Research in NLP lacks geographic diversity, and the question of how NLP ...
Conditional masked language model (CMLM) training has proven successful ...
Sequence-to-sequence learning involves a trade-off between signal streng...
Transformers have shown great promise as an approach to Neural Machine
T...
Africa has over 2000 languages. Despite this, African languages account ...
We present Joey NMT, a minimalist neural machine translation toolkit bas...
Not all types of supervision signals are created equal: Different types ...
Most modern neural machine translation (NMT) systems rely on presegmente...
Most modern neural machine translation (NMT) systems rely on presegmente...
Back-translation has become a commonly employed heuristic for semi-super...
We present a study on reinforcement learning (RL) from human bandit feed...
We present an approach to interactive-predictive neural machine translat...
We present the first real-world application of methods for improving neu...
We introduce and describe the results of a novel shared task on bandit
l...
Bandit structured prediction describes a stochastic optimization framewo...
Stochastic structured prediction under bandit feedback follows a learnin...