373 citations · 548 across the 15 of their papers we have counts for
16 papers · 1 filter
Merging Text Transformer Models from Different Initializations
Neha Verma, Maha Elbayad
Recent work on permutation-based model merging has shown impressive low- or zero-barrier mode connectivity between models from completely different initializations. However, this l…
Spirit LM: Interleaved Spoken and Written Language Model
Tu Anh Nguyen, Benjamin Muller, Bokai Yu +13
We introduce Spirit LM, a foundation multimodal language model that freely mixes text and speech. Our model is based on a 7B pretrained text language model that we extend to the sp…
Seamless: Multilingual Expressive and Streaming Speech Translation
Seamless Communication, Loïc Barrault, Yu-An Chung +62
Large-scale automatic speech translation systems today lack key features that help machine-mediated communication feel seamless when compared to human-to-human dialogue. In this wo…
Added Toxicity Mitigation at Inference Time for Multimodal and Massively Multilingual Translation
Marta R. Costa-jussà, David Dale, Maha Elbayad +1
Added toxicity in the context of translation refers to the fact of producing a translation output with more toxicity than there exists in the input. In this paper, we present MinTo…
SeamlessM4T: Massively Multilingual & Multimodal Machine Translation
Seamless Communication, Loïc Barrault, Yu-An Chung +65
What does it take to create the Babel Fish, a tool that can help individuals translate speech between any two languages? While recent breakthroughs in text-based models have pushed…
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
Haoran Xu, Maha Elbayad, Kenton Murray +2
Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computation…
Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages
Simeng Sun, Maha Elbayad, Anna Sun +1
With multilingual machine translation (MMT) models continuing to grow in size and number of supported languages, it is natural to reuse and upgrade existing models to save computat…
Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation
Maha Elbayad, Anna Sun, Shruti Bhosale
Sparsely gated Mixture of Experts (MoE) models have been shown to be a compute-efficient method to scale model capacity for multilingual machine translation. However, for low-resou…
Causes and Cures for Interference in Multilingual Translation
Uri Shaham, Maha Elbayad, Vedanuj Goswami +2
Multilingual machine translation models can benefit from synergy between different language pairs, but also suffer from interference. While there is a growing number of sophisticat…
No Language Left Behind: Scaling Human-Centered Machine Translation
NLLB Team, Marta R. Costa-jussà, James Cross +36
Driven by the goal of eradicating language barriers on a global scale, machine translation has solidified itself as a key focus of artificial intelligence research today. However,…
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English
Maha Elbayad, Michael Ustaszewski, Emmanuelle Esperança-Rodier +3
We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. Two sequence-to-sequence models: convolutional Pervasive Attentio…
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020
Maha Elbayad, Ha Nguyen, Fethi Bougares +5
This paper describes the ON-TRAC Consortium translation systems developed for two challenge tracks featured in the Evaluation Campaign of IWSLT 2020, offline speech translation and…
Efficient Wait-k Models for Simultaneous Machine Translation
Maha Elbayad, Laurent Besacier, Jakob Verbeek
Simultaneous machine translation consists in starting output generation before the entire input sequence is available. Wait-k decoders offer a simple but efficient approach for thi…
Depth-Adaptive Transformer
Maha Elbayad, Jiatao Gu, Edouard Grave +1
State of the art sequence-to-sequence models for large scale tasks perform a fixed number of computations for each input sequence regardless of whether it is easy or hard to proces…
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Maha Elbayad, Laurent Besacier, Jakob Verbeek
Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on…
Token-level and sequence-level loss smoothing for RNN language models
Maha Elbayad, Laurent Besacier, Jakob Verbeek
Despite the effectiveness of recurrent neural network language models, their maximum likelihood estimation suffers from two limitations. It treats all sentences that do not match t…