research
∙
03/31/2023
Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
In end-to-end (E2E) speech recognition models, a representational tight-...
share
research
∙
11/16/2022
Towards Computationally Verifiable Semantic Grounding for Language Models
The paper presents an approach to semantic grounding of language models ...
research
∙
09/16/2021
Scaling Laws for Neural Machine Translation
We present an empirical study of scaling properties of encoder-decoder T...
research
∙
10/26/2020
Data Troubles in Sentence Level Confidence Estimation for Machine Translation
The paper investigates the feasibility of confidence estimation for neur...
research
∙
05/02/2020
Practical Perspectives on Quality Estimation for Machine Translation
Sentence level quality estimation (QE) for machine translation (MT) atte...
research
∙
01/14/2020
Faster Transformer Decoding: N-gram Masked Self-Attention
Motivated by the fact that most of the information relevant to the predi...
research
∙
06/15/2019
Tagged Back-Translation
Recent work in Neural Machine Translation (NMT) has shown significant qu...
research
∙
06/03/2019
Dynamically Composing Domain-Data Selection with Clean-Data Selection by "Co-Curricular Learning" for Neural Machine Translation
Noise and domain are important aspects of data quality for neural machin...
research
∙
02/21/2019
Lingvo: a Modular and Scalable Framework for Sequence-to-Sequence Modeling
Lingvo is a Tensorflow framework offering a complete solution for collab...
research
∙
08/31/2018
Denoising Neural Machine Translation Training with Trusted Data and Online Data Selection
Measuring domain relevance of data and identifying or selecting well-fit...
research
∙
06/18/2018
GroupReduce: Block-Wise Low-Rank Approximation for Neural Language Model Shrinking
Model compression is essential for serving large deep neural nets on dev...
research
∙
03/31/2017
N-gram Language Modeling using Recurrent Neural Network Estimation
We investigate the effective memory depth of RNN models by using them fo...
research
∙
11/05/2015
Multinomial Loss on Held-out Data for the Sparse Non-negative Matrix Language Model
We describe Sparse Non-negative Matrix (SNM) language model estimation u...
research
∙
12/03/2014