Behavioral testing in NLP allows fine-grained evaluation of systems by
e...
Self-training has been shown to be helpful in addressing data scarcity f...
Code switching (CS) refers to the phenomenon of interchangeably using wo...
Using end-to-end models for speech translation (ST) has increasingly bee...
The conventional paradigm in speech translation starts with a speech
rec...
Variational Neural Machine Translation (VNMT) is an attractive framework...
Over its three decade history, speech translation has experienced severa...
User studies have shown that reducing the latency of our simultaneous le...
Lattices are an efficient and effective method to encode ambiguity of
up...
Previous work on end-to-end translation from speech has primarily used
f...
Spoken language translation applications for speech suffer due to
conver...
Speech translation has traditionally been approached through cascaded mo...
Using paraphrases, the expression of the same semantic meaning in differ...
Through the development of neural machine translation, the quality of ma...
We work on translation from rich-resource languages to low-resource
lang...
Self-attention is a method of encoding sequences of vectors by relating ...
This paper describes XNMT, the eXtensible Neural Machine Translation too...
We investigate the problem of manually correcting errors from an automat...
Connectionist Temporal Classification has recently attracted a lot of
in...
The input to a neural sequence-to-sequence model is often determined by ...