English
Related papers

Related papers: What changes when you randomly choose BPE merge op…

200 papers

Minimum Bayes risk (MBR) decoding generates high-quality translations by maximizing the expected utility of output candidates, but it evaluates all pairwise scores over the candidate set; hence, it takes quadratic time with respect to the…

Computation and Language · Computer Science 2025-12-02 Koki Natsumi , Hiroyuki Deguchi , Yusuke Sakai , Hidetaka Kamigaito , Taro Watanabe

Unsupervised machine translation---i.e., not assuming any cross-lingual supervision signal, whether a dictionary, translations, or comparable corpora---seems impossible, but nevertheless, Lample et al. (2018) recently proposed a fully…

Computation and Language · Computer Science 2018-05-10 Anders Søgaard , Sebastian Ruder , Ivan Vulić

Model merging aims to integrate multiple task-specific models into a unified model that inherits the capabilities of the task-specific models, without additional training. Existing model merging methods often lack consideration of the…

Computation and Language · Computer Science 2025-08-07 Yue Zhou , Yi Chang , Yuan Wu

We propose a novel method for translation selection in statistical machine translation, in which a convolutional neural network is employed to judge the similarity between a phrase pair in two languages. The specifically designed…

Computation and Language · Computer Science 2015-06-25 Zhaopeng Tu , Baotian Hu , Zhengdong Lu , Hang Li

Neural metrics have achieved impressive correlation with human judgements in the evaluation of machine translation systems, but before we can safely optimise towards such metrics, we should be aware of (and ideally eliminate) biases toward…

Computation and Language · Computer Science 2022-09-27 Chantal Amrhein , Rico Sennrich

We employ the Bayesian improved cross entropy (BiCE) method for rare event estimation in static networks and choose the categorical mixture as the parametric family to capture the dependence among network components. At each iteration of…

Methodology · Statistics 2023-09-25 Jianpeng Chan , Iason Papaioannou , Daniel Straub

We present a deep generative model of bilingual sentence pairs for machine translation. The model generates source and target sentences jointly from a shared latent representation and is parameterised by neural networks. We perform…

Computation and Language · Computer Science 2019-06-03 Bryan Eikema , Wilker Aziz

Multilingual language models have shown decent performance in multilingual and cross-lingual natural language understanding tasks. However, the power of these multilingual models in code-switching tasks has not been fully explored. In this…

Computation and Language · Computer Science 2021-03-25 Genta Indra Winata , Samuel Cahyawijaya , Zihan Liu , Zhaojiang Lin , Andrea Madotto , Pascale Fung

The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages. Despite impressive empirical results and an…

Machine Learning · Computer Science 2020-08-12 Han Zhao , Junjie Hu , Andrej Risteski

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

This paper illustrates our approach to the shared task on large-scale multilingual machine translation in the sixth conference on machine translation (WMT-21). This work aims to build a single multilingual translation system with a…

Computation and Language · Computer Science 2021-09-21 Baohao Liao , Shahram Khadivi , Sanjika Hewavitharana

The Bayesian approach to machine learning amounts to computing posterior distributions of random variables from a probabilistic model of how the variables are related (that is, a prior distribution) and a set of observations of variables.…

Logic in Computer Science · Computer Science 2015-07-01 Johannes Borgström , Andrew D Gordon , Michael Greenberg , James Margetson , Jurgen Van Gael

Despite some empirical success at correcting exposure bias in machine translation, scheduled sampling algorithms suffer from a major drawback: they incorrectly assume that words in the reference translations and in sampled sequences are…

Computation and Language · Computer Science 2019-05-07 Weijia Xu , Xing Niu , Marine Carpuat

This paper reviews the basic ideas behind a Bayesian unfolding published some years ago and improves their implementation. In particular, uncertainties are now treated at all levels by probability density functions and their propagation is…

Data Analysis, Statistics and Probability · Physics 2010-10-05 G. D'Agostini

Bilingual word embeddings represent words of two languages in the same space, and allow to transfer knowledge from one language to the other without machine translation. The main approach is to train monolingual embeddings first and then…

Computation and Language · Computer Science 2018-04-24 J. Goikoetxea , A. Soroa , E. Agirre

Zero-shot neural machine translation is an attractive goal because of the high cost of obtaining data and building translation systems for new translation directions. However, previous papers have reported mixed success in zero-shot…

Computation and Language · Computer Science 2020-11-04 Annette Rios , Mathias Müller , Rico Sennrich

Approximate Bayesian inference for neural networks is considered a robust alternative to standard training, often providing good performance on out-of-distribution data. However, Bayesian neural networks (BNNs) with high-fidelity…

Machine Learning · Computer Science 2021-12-07 Pavel Izmailov , Patrick Nicholson , Sanae Lotfi , Andrew Gordon Wilson

Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…

Computation and Language · Computer Science 2019-12-10 Carlos Escolano , Marta R. Costa-jussà , José A. R. Fonollosa

Multi-head attentive neural architectures have achieved state-of-the-art results on a variety of natural language processing tasks. Evidence has shown that they are overparameterized; attention heads can be pruned without significant…

Computation and Language · Computer Science 2020-05-15 Hao Peng , Roy Schwartz , Dianqi Li , Noah A. Smith

Computing the exact likelihood of data in large Bayesian networks consisting of thousands of vertices is often a difficult task. When these models contain many deterministic conditional probability tables and when the observed values are…

Computation · Statistics 2012-06-26 Ydo Wexler , Dan Geiger