English
Related papers

Related papers: Tricks for Training Sparse Translation Models

200 papers

Multilingual machine translation has attracted much attention recently due to its support of knowledge transfer among languages and the low cost of training and deployment compared with numerous bilingual models. A known challenge of…

Computation and Language · Computer Science 2022-01-25 Hongyu Gong , Xian Li , Dmitriy Genzel

To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we…

Machine Learning · Computer Science 2019-09-17 Sébastien Jean , Orhan Firat , Melvin Johnson

Multi-task learning (MTL) aims to improve generalization performance by learning multiple related tasks simultaneously. While sometimes the underlying task relationship structure is known, often the structure needs to be estimated from data…

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Machine Learning · Computer Science 2026-04-27 Hongtao Xu , Jianchao Tan , Yuxuan Hu , Pengju Lu , Hongyu Wang , Pingwei Sun , Yerui Sun , Yuchen Xie , Xunliang Cai , Mingzhen Li , Weile Jia

When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…

Computation and Language · Computer Science 2020-09-08 Xinyi Wang , Yulia Tsvetkov , Graham Neubig

We introduce a new balanced assignment of experts (BASE) layer for large language models that greatly simplifies existing high capacity sparse layers. Sparse layers can dramatically improve the efficiency of training and inference by…

Computation and Language · Computer Science 2021-04-01 Mike Lewis , Shruti Bhosale , Tim Dettmers , Naman Goyal , Luke Zettlemoyer

We investigate the use of sparse coding and dictionary learning in the context of multitask and transfer learning. The central assumption of our learning method is that the tasks parameters are well approximated by sparse linear…

Machine Learning · Computer Science 2014-06-17 Andreas Maurer , Massimiliano Pontil , Bernardino Romera-Paredes

A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy is usually used to…

Computation and Language · Computer Science 2022-09-13 Shiyue Zhang , Vishrav Chaudhary , Naman Goyal , James Cross , Guillaume Wenzek , Mohit Bansal , Francisco Guzman

Large Transformer models yield impressive results on many tasks, but are expensive to train, or even fine-tune, and so slow at decoding that their use and study becomes out of reach. We address this problem by leveraging sparsity. We study…

Learned data models based on sparsity are widely used in signal processing and imaging applications. A variety of methods for learning synthesis dictionaries, sparsifying transforms, etc., have been proposed in recent years, often imposing…

Machine Learning · Computer Science 2018-10-22 Saiprasad Ravishankar , Brendt Wohlberg

In multilingual neural machine translation, it has been shown that sharing a single translation model between multiple languages can achieve competitive performance, sometimes even leading to performance gains over bilingually trained…

Computation and Language · Computer Science 2018-09-14 Devendra Singh Sachan , Graham Neubig

Despite increasing focus on data publication and discovery in materials science and related fields, the global view of materials data is highly sparse. This sparsity encourages training models on the union of multiple datasets, but simple…

Machine Learning · Computer Science 2017-11-15 Maxwell L. Hutchinson , Erin Antono , Brenna M. Gibbons , Sean Paradiso , Julia Ling , Bryce Meredig

We focus on multi-domain Neural Machine Translation, with the goal of developing efficient models which can handle data from various domains seen during training and are robust to domains unseen during training. We hypothesize that Sparse…

Computation and Language · Computer Science 2024-07-02 Nadezhda Chirkova , Vassilina Nikoulina , Jean-Luc Meunier , Alexandre Bérard

In low-resource multilingual speech-to-text translation, uniform architectural sharing across languages frequently introduces representation conflicts that impede convergence. This work proposes a principled methodology to automatically…

Computation and Language · Computer Science 2026-03-30 Ruiyan Sun , Satoshi Nakamura

We investigate the training of sparse layers that use different parameters for different inputs based on hashing in large Transformer models. Specifically, we modify the feedforward layer to hash to different sets of weights depending on…

Machine Learning · Computer Science 2021-07-21 Stephen Roller , Sainbayar Sukhbaatar , Arthur Szlam , Jason Weston

Merging parameter-efficient task experts has recently gained growing attention as a way to build modular architectures that can be rapidly adapted on the fly for specific downstream tasks, without requiring additional fine-tuning.…

We consider a problem in Multi-Task Learning (MTL) where multiple linear models are jointly trained on a collection of datasets ("tasks"). A key novelty of our framework is that it allows the sparsity pattern of regression coefficients and…

Distributed training is the de facto standard to scale up the training of deep learning models with multiple GPUs. Its performance bottleneck lies in communications for gradient synchronization. Although high tensor sparsity is widely…

Machine Learning · Computer Science 2024-12-17 Zhuang Wang , Zhaozhuo Xu , Jingyi Xi , Yuke Wang , Anshumali Shrivastava , T. S. Eugene Ng

Sparsity of channel in the next generation of wireless communication for massive multiple-input-multiple-output (MIMO) systems can be exploited to reduce the overhead in the training. The multitask (MT)-sparse Bayesian learning (SBL) is…

Information Theory · Computer Science 2024-10-30 Arash Shahmansoori

Achieving human-level translations requires leveraging context to ensure coherence and handle complex phenomena like pronoun disambiguation. Sparsity of contextually rich examples in the standard training data has been hypothesized as the…

Computation and Language · Computer Science 2025-09-18 Paweł Mąka , Yusuf Can Semerci , Jan Scholtes , Gerasimos Spanakis
‹ Prev 1 2 3 10 Next ›