Data scarcity is a crucial issue for the development of highly multiling...
Large, multilingual language models exhibit surprisingly good zero- or
f...
We demonstrate the potential of few-shot translation systems, trained wi...
Large language models (LLMs) that have been trained on multilingual but ...
End-to-end speech-to-speech translation (S2ST) without relying on
interm...
We introduce XTREME-S, a new benchmark to evaluate universal cross-lingu...
In this work, we study the effect of varying the architecture and traini...
We present mSLAM, a multilingual Speech and LAnguage Model that learns
c...
Non-autoregressive (NAR) machine translation has recently achieved
signi...
We present an empirical study of scaling properties of encoder-decoder
T...
Reference-free evaluation has the potential to make machine translation
...
Neural Machine Translation (NMT) models have demonstrated strong state o...
Automatic evaluation comparing candidate translations to human-generated...
Conditional masked language model (CMLM) training has proven successful ...
There has been great progress in improving streaming machine translation...
We investigate the problem of simultaneous machine translation of long-f...
We introduce our efforts towards building a universal neural machine
tra...
Simultaneous machine translation begins to translate each source sentenc...
Simultaneous machine translation attempts to translate a source sentence...
We consider the problem of making efficient use of heterogeneous trainin...
Lingvo is a Tensorflow framework offering a complete solution for
collab...
We consider the problem of designing an artificial agent capable of
inte...
Neural approaches to sequence labeling often use a Conditional Random Fi...
Translating characters instead of words or word-fragments has the potent...
Neural machine translation represents an exciting leap forward in transl...
We propose a multi-view network for text classification. Our method
auto...