Maha Elbayad


pdf bib
Fixing MoE Over-Fitting on Low-Resource Languages in Multilingual Machine Translation
Maha Elbayad | Anna Sun | Shruti Bhosale
Findings of the Association for Computational Linguistics: ACL 2023

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-resource tasks, MoE models severely over-fit. We show effective regularization strategies, namely dropout techniques for MoE layers in EOM and FOM, Conditional MoE Routing and Curriculum Learning methods that prevent over-fitting and improve the performance of MoE models on low-resource tasks without adversely affecting high-resource tasks. On a massively multilingual machine translation benchmark, our strategies result in about +1 chrF++ improvement in very low resource language pairs. We perform an extensive analysis of the learned MoE routing to better understand the impact of our regularization methods and how we can improve them.

pdf bib
Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity
Haoran Xu | Maha Elbayad | Kenton Murray | Jean Maillard | Vedanuj Goswami
Findings of the Association for Computational Linguistics: EMNLP 2023

Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computational requirements per token. However, recent studies have established that MoE models are inherently parameter-inefficient as the improvement in performance diminishes with an increasing number of experts. We hypothesize this parameter inefficiency is a result of all experts having equal capacity, which may not adequately meet the varying complexity requirements of different tokens or tasks. In light of this, we propose Stratified Mixture of Experts (SMoE) models, which feature a stratified structure and can assign dynamic capacity to different tokens. We demonstrate the effectiveness of SMoE on three multilingual machine translation benchmarks, containing 4, 15, and 94 language pairs, respectively. We show that SMoE outperforms multiple state-of-the-art MoE models with the same or fewer parameters.

pdf bib
Causes and Cures for Interference in Multilingual Translation
Uri Shaham | Maha Elbayad | Vedanuj Goswami | Omer Levy | Shruti Bhosale
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

Multilingual machine translation models can benefit from synergy between different language pairs, but also suffer from interference. While there is a growing number of sophisticated methods that aim to eliminate interference, our understanding of interference as a phenomenon is still limited. This work identifies the main factors that contribute to interference in multilingual machine translation. Through systematic experimentation, we find that interference (or synergy) are primarily determined by model size, data size, and the proportion of each language pair within the total dataset. We observe that substantial interference occurs mainly when the model is very small with respect to the available training data, and that using standard transformer configurations with less than one billion parameters largely alleviates interference and promotes synergy. Moreover, we show that tuning the sampling temperature to control the proportion of each language pair in the data is key to balancing the amount of interference between low and high resource language pairs effectively, and can lead to superior performance overall.

pdf bib
Efficiently Upgrading Multilingual Machine Translation Models to Support More Languages
Simeng Sun | Maha Elbayad | Anna Sun | James Cross
Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics

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 computation as data becomes available in more languages. However, adding new languages requires updating the vocabulary, which complicates the reuse of embeddings. The question of how to reuse existing models while also making architectural changes to provide capacity for both old and new languages has also not been closely studied. In this work, we introduce three techniques that help speed up the effective learning of new languages and alleviate catastrophic forgetting despite vocabulary and architecture mismatches. Our results show that by (1) carefully initializing the network, (2) applying learning rate scaling, and (3) performing data up-sampling, it is possible to exceed the performance of a same-sized baseline model with 30% computation and recover the performance of a larger model trained from scratch with over 50% reduction in computation. Furthermore, our analysis reveals that the introduced techniques help learn new directions more effectively and alleviate catastrophic forgetting at the same time. We hope our work will guide research into more efficient approaches to growing languages for these MMT models and ultimately maximize the reuse of existing models.


pdf bib
Findings of the IWSLT 2022 Evaluation Campaign
Antonios Anastasopoulos | Loïc Barrault | Luisa Bentivogli | Marcely Zanon Boito | Ondřej Bojar | Roldano Cattoni | Anna Currey | Georgiana Dinu | Kevin Duh | Maha Elbayad | Clara Emmanuel | Yannick Estève | Marcello Federico | Christian Federmann | Souhir Gahbiche | Hongyu Gong | Roman Grundkiewicz | Barry Haddow | Benjamin Hsu | Dávid Javorský | Vĕra Kloudová | Surafel Lakew | Xutai Ma | Prashant Mathur | Paul McNamee | Kenton Murray | Maria Nǎdejde | Satoshi Nakamura | Matteo Negri | Jan Niehues | Xing Niu | John Ortega | Juan Pino | Elizabeth Salesky | Jiatong Shi | Matthias Sperber | Sebastian Stüker | Katsuhito Sudoh | Marco Turchi | Yogesh Virkar | Alexander Waibel | Changhan Wang | Shinji Watanabe
Proceedings of the 19th International Conference on Spoken Language Translation (IWSLT 2022)

The evaluation campaign of the 19th International Conference on Spoken Language Translation featured eight shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Speech to speech translation, (iv) Low-resource speech translation, (v) Multilingual speech translation, (vi) Dialect speech translation, (vii) Formality control for speech translation, (viii) Isometric speech translation. A total of 27 teams participated in at least one of the shared tasks. This paper details, for each shared task, the purpose of the task, the data that were released, the evaluation metrics that were applied, the submissions that were received and the results that were achieved.

pdf bib
Rethinking the Design of Sequence-to-Sequence Models for Efficient Machine Translation
Maha Elbayad
Proceedings of the 23rd Annual Conference of the European Association for Machine Translation


pdf bib
Proceedings of the Second Workshop on Automatic Simultaneous Translation
Hua Wu | Colin Cherry | Liang Huang | Zhongjun He | Qun Liu | Maha Elbayad | Mark Liberman | Haifeng Wang | Mingbo Ma | Ruiqing Zhang
Proceedings of the Second Workshop on Automatic Simultaneous Translation

pdf bib
Antonios Anastasopoulos | Ondřej Bojar | Jacob Bremerman | Roldano Cattoni | Maha Elbayad | Marcello Federico | Xutai Ma | Satoshi Nakamura | Matteo Negri | Jan Niehues | Juan Pino | Elizabeth Salesky | Sebastian Stüker | Katsuhito Sudoh | Marco Turchi | Alexander Waibel | Changhan Wang | Matthew Wiesner
Proceedings of the 18th International Conference on Spoken Language Translation (IWSLT 2021)

The evaluation campaign of the International Conference on Spoken Language Translation (IWSLT 2021) featured this year four shared tasks: (i) Simultaneous speech translation, (ii) Offline speech translation, (iii) Multilingual speech translation, (iv) Low-resource speech translation. A total of 22 teams participated in at least one of the tasks. This paper describes each shared task, data and evaluation metrics, and reports results of the received submissions.


pdf bib
Online Versus Offline NMT Quality: An In-depth Analysis on English-German and German-English
Maha Elbayad | Michael Ustaszewski | Emmanuelle Esperança-Rodier | Francis Brunet-Manquat | Jakob Verbeek | Laurent Besacier
Proceedings of the 28th International Conference on Computational Linguistics

We conduct in this work an evaluation study comparing offline and online neural machine translation architectures. Two sequence-to-sequence models: convolutional Pervasive Attention (Elbayad et al. 2018) and attention-based Transformer (Vaswani et al. 2017) are considered. We investigate, for both architectures, the impact of online decoding constraints on the translation quality through a carefully designed human evaluation on English-German and German-English language pairs, the latter being particularly sensitive to latency constraints. The evaluation results allow us to identify the strengths and shortcomings of each model when we shift to the online setup.

pdf bib
ON-TRAC Consortium for End-to-End and Simultaneous Speech Translation Challenge Tasks at IWSLT 2020
Maha Elbayad | Ha Nguyen | Fethi Bougares | Natalia Tomashenko | Antoine Caubrière | Benjamin Lecouteux | Yannick Estève | Laurent Besacier
Proceedings of the 17th International Conference on Spoken Language Translation

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 simultaneous speech translation. ON-TRAC Consortium is composed of researchers from three French academic laboratories: LIA (Avignon Université), LIG (Université Grenoble Alpes), and LIUM (Le Mans Université). Attention-based encoder-decoder models, trained end-to-end, were used for our submissions to the offline speech translation track. Our contributions focused on data augmentation and ensembling of multiple models. In the simultaneous speech translation track, we build on Transformer-based wait-k models for the text-to-text subtask. For speech-to-text simultaneous translation, we attach a wait-k MT system to a hybrid ASR system. We propose an algorithm to control the latency of the ASR+MT cascade and achieve a good latency-quality trade-off on both subtasks.


pdf bib
Token-level and sequence-level loss smoothing for RNN language models
Maha Elbayad | Laurent Besacier | Jakob Verbeek
Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)

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 the ground truth as equally poor, ignoring the structure of the output space. Second, it suffers from ’exposure bias’: during training tokens are predicted given ground-truth sequences, while at test time prediction is conditioned on generated output sequences. To overcome these limitations we build upon the recent reward augmented maximum likelihood approach that encourages the model to predict sentences that are close to the ground truth according to a given performance metric. We extend this approach to token-level loss smoothing, and propose improvements to the sequence-level smoothing approach. Our experiments on two different tasks, image captioning and machine translation, show that token-level and sequence-level loss smoothing are complementary, and significantly improve results.

pdf bib
Pervasive Attention: 2D Convolutional Neural Networks for Sequence-to-Sequence Prediction
Maha Elbayad | Laurent Besacier | Jakob Verbeek
Proceedings of the 22nd Conference on Computational Natural Language Learning

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 the input encoding. Both are interfaced with an attention mechanism that recombines a fixed encoding of the source tokens based on the decoder state. We propose an alternative approach which instead relies on a single 2D convolutional neural network across both sequences. Each layer of our network re-codes source tokens on the basis of the output sequence produced so far. Attention-like properties are therefore pervasive throughout the network. Our model yields excellent results, outperforming state-of-the-art encoder-decoder systems, while being conceptually simpler and having fewer parameters.