Measuring automatic speech recognition (ASR) system quality is critical ...
An effective recipe for building seq2seq, non-autoregressive, task-orien...
Word Error Rate (WER) has been the predominant metric used to evaluate t...
Being able to parse code-switched (CS) utterances, such as Spanish+Engli...
Scaling semantic parsing models for task-oriented dialog systems to new
...
The task of identifying out-of-domain (OOD) input examples directly at
t...
Anahita is an autonomous underwater vehicle which is currently being
dev...
We introduce PyText - a deep learning based NLP modeling framework built...