English
Related papers

Related papers: Data Compression: Multi-Term Approach

200 papers

In this paper, we re-examine the Markov property in the context of neural machine translation. We design a Markov Autoregressive Transformer~(MAT) and undertake a comprehensive assessment of its performance across four WMT benchmarks. Our…

Computation and Language · Computer Science 2024-02-06 Cunxiao Du , Hao Zhou , Zhaopeng Tu , Jing Jiang

Pretrained contextualized representations offer great success for many downstream tasks, including document ranking. The multilingual versions of such pretrained representations provide a possibility of jointly learning many languages with…

Information Retrieval · Computer Science 2021-09-16 Zhiqi Huang , Hamed Bonab , Sheikh Muhammad Sarwar , Razieh Rahimi , James Allan

Post-training compression of Transformer models commonly relies on truncated singular value decomposition (SVD). However, enforcing a single shared subspace can degrade accuracy even at moderate compression. Sparse dictionary learning…

Machine Learning · Computer Science 2026-02-18 Denis Makhov , Dmitriy Shopkhoev , Magauiya Zhussip , Ammar Ali , Baher Mohammad , Stamatios Lefkimmiatis

Multi-task learning (MTL) aims to improve the generalization performance of multiple tasks by exploiting the shared factors among them. Various metrics (e.g., F-score, Area Under the ROC Curve) are used to evaluate the performances of MTL…

Machine Learning · Computer Science 2022-10-13 Ge-Yang Ke , Yan Pan , Jian Yin , Chang-Qin Huang

The influence-matrix formalism provides an alternative route to the classical simulation of quantum dynamics. Because influence matrices retain information only about the effective bath seen by local observables, they are expected to be…

Quantum Physics · Physics 2026-05-14 Cathy Li , Bruno Bertini , Katja Klobas , Tianci Zhou

Neural Machine Translation (NMT), like many other deep learning domains, typically suffers from over-parameterization, resulting in large storage sizes. This paper examines three simple magnitude-based pruning schemes to compress NMT…

Artificial Intelligence · Computer Science 2016-07-01 Abigail See , Minh-Thang Luong , Christopher D. Manning

Large-scale transformer models have shown remarkable performance in language modelling tasks. However, such models feature billions of parameters, leading to difficulties in their deployment and prohibitive training costs from scratch. To…

Artificial Intelligence · Computer Science 2023-06-06 Viktoriia Chekalina , Georgii Novikov , Julia Gusak , Ivan Oseledets , Alexander Panchenko

Manipulating training data leads to robust neural models for MT.

Computation and Language · Computer Science 2024-02-23 Rumeng Li , Xun Wang , Hong Yu

Neural machine translation (NMT) models are typically trained with fixed-size input and output vocabularies, which creates an important bottleneck on their accuracy and generalization capability. As a solution, various studies proposed…

Computation and Language · Computer Science 2018-05-08 Duygu Ataman , Marcello Federico

In this note, we investigate how well we can reconstruct the best rank-$r$ approximation of a large matrix from a small number of its entries. We show that even if a data matrix is of full rank and cannot be approximated well by a low-rank…

Methodology · Statistics 2021-11-12 Shun Xu , Ming Yuan

The Tensor-Train (TT) format is a highly compact low-rank representation for high-dimensional tensors. TT is particularly useful when representing approximations to the solutions of certain types of parametrized partial differential…

Large time series models (LTMs) have emerged as powerful tools for universal forecasting, yet they often struggle with the inherent diversity and nonstationarity of real-world time series data, leading to an unsatisfactory trade-off between…

Machine Learning · Computer Science 2026-03-03 Yunzhong Qiu , Zhiyao Cen , Zhongyi Pei , Chen Wang , Jianmin Wang

We consider the analysis of high dimensional data given in the form of a matrix with columns consisting of observations and rows consisting of features. Often the data is such that the observations do not reside on a regular grid, and the…

Machine Learning · Statistics 2017-08-22 Gal Mishne , Ronen Talmon , Israel Cohen , Ronald R. Coifman , Yuval Kluger

We propose a flexible and theoretically supported framework for scalable nonnegative matrix factorization. The goal is to find nonnegative low-rank components directly from compressed measurements, accessing the original data only once or…

Optimization and Control · Mathematics 2026-02-17 Abraar Chaudhry , Elizaveta Rebrova

We propose and analyse a reduced-rank method for solving least-squares regression problems with infinite dimensional output. We derive learning bounds for our method, and study under which setting statistical performance is improved in…

Machine Learning · Statistics 2022-11-17 Luc Brogat-Motte , Alessandro Rudi , Céline Brouard , Juho Rousu , Florence d'Alché-Buc

Transfer learning aims to faciliate learning tasks in a label-scarce target domain by leveraging knowledge from a related source domain with plenty of labeled data. Often times we may have multiple domains with little or no labeled data as…

Machine Learning · Computer Science 2017-11-10 Tianchun Wang

While modern machine translation has relied on large parallel corpora, a recent line of work has managed to train Neural Machine Translation (NMT) systems from monolingual corpora only (Artetxe et al., 2018c; Lample et al., 2018). Despite…

Computation and Language · Computer Science 2021-12-28 Mikel Artetxe , Gorka Labaka , Eneko Agirre

Neural machine translation (NMT) has recently gained widespread attention because of its high translation accuracy. However, it shows poor performance in the translation of long sentences, which is a major issue in low-resource languages.…

Computation and Language · Computer Science 2021-04-20 Seiichiro Kondo , Kengo Hotate , Masahiro Kaneko , Mamoru Komachi

Translating major language resources to build minor language resources becomes a widely-used approach. Particularly in translating complex data points composed of multiple components, it is common to translate each component separately.…

Computation and Language · Computer Science 2024-12-03 Hyeonseok Moon , Seungyoon Lee , Seongtae Hong , Seungjun Lee , Chanjun Park , Heuiseok Lim

The tensor train rank (TT-rank) has achieved promising results in tensor completion due to its ability to capture the global low-rankness of higher-order (>3) tensors. On the other hand, recently, quaternions have proven to be a very…

Image and Video Processing · Electrical Eng. & Systems 2022-09-08 Jifei Miao , Kit Ian Kou , Liqiao Yang , Dong Cheng