-
Pseudolikelihood Reranking with Masked Language Models
We rerank with scores from pretrained masked language models like BERT t...
10/31/2019 ∙ by Julian Salazar, et al. ∙
15
∙
share
read it
-
Syntactic and Semantic Features For Code-Switching Factored Language Models
This paper presents our latest investigations on different features for ...
10/04/2017 ∙ by Heike Adel, et al. ∙
0
∙
share
read it
-
Exploiting Out-of-Domain Data Sources for Dialectal Arabic Statistical Machine Translation
Statistical machine translation for dialectal Arabic is characterized by...
09/07/2015 ∙ by Katrin Kirchhoff, et al. ∙
0
∙
share
read it
-
Context Models for OOV Word Translation in Low-Resource Languages
Out-of-vocabulary word translation is a major problem for the translatio...
01/26/2018 ∙ by Angli Liu, et al. ∙
0
∙
share
read it
-
Self-Attention Networks for Connectionist Temporal Classification in Speech Recognition
Self-attention has demonstrated great success in sequence-to-sequence ta...
01/22/2019 ∙ by Julian Salazar, et al. ∙
0
∙
share
read it
-
Simple, Fast, Accurate Intent Classification and Slot Labeling
In real-time dialogue systems running at scale, there is a tradeoff betw...
03/19/2019 ∙ by Arshit Gupta, et al. ∙
0
∙
share
read it
-
Multi-stream Network With Temporal Attention For Environmental Sound Classification
Environmental sound classification systems often do not perform robustly...
01/24/2019 ∙ by Xinyu Li, et al. ∙
0
∙
share
read it
-
Contextual Phonetic Pretraining for End-to-end Utterance-level Language and Speaker Recognition
Pretrained contextual word representations in NLP have greatly improved ...
06/30/2019 ∙ by Shaoshi Ling, et al. ∙
0
∙
share
read it
-
Deep Contextualized Acoustic Representations For Semi-Supervised Speech Recognition
We propose a novel approach to semi-supervised automatic speech recognit...
12/03/2019 ∙ by Shaoshi Ling, et al. ∙
0
∙
share
read it
