Token-level and sequence-level loss smoothing for RNN language models
Paper
•
1805.05062
•
Published
Maha Elbayad
elbayadm
AI & ML interests
NLP, speech, translation
Organizations
authored
4
papers
7 months ago
Efficient Wait-k Models for Simultaneous Machine Translation
Paper
•
2005.08595
•
Published
Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation
Paper
•
2311.06532
•
Published
Large Concept Models: Language Modeling in a Sentence Representation Space
Paper
•
2412.08821
•
Published
•
15
authored
10
papers
over 1 year ago
SpiRit-LM: Interleaved Spoken and Written Language Model
Paper
•
2402.05755
•
Published
•
15
Seamless: Multilingual Expressive and Streaming Speech Translation
Paper
•
2312.05187
•
Published
•
14
No Language Left Behind: Scaling Human-Centered Machine Translation
Paper
•
2207.04672
•
Published
•
2
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Paper
•
1808.03867
•
Published
SeamlessM4T-Massively Multilingual & Multimodal Machine Translation
Paper
•
2308.11596
•
Published
•
1
Depth-Adaptive Transformer
Paper
•
1910.10073
•
Published
•
1
Causes and Cures for Interference in Multilingual Translation
Paper
•
2212.07530
•
Published
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
Paper
•
2305.02176
•
Published
Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages
Paper
•
2302.03528
•
Published
Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation
Paper
•
2212.07571
•
Published