Related papers: Dynamic Data Selection and Weighting for Iterative…
Despite impressive empirical successes of neural machine translation (NMT) on standard benchmarks, limited parallel data impedes the application of NMT models to many language pairs. Data augmentation methods such as back-translation make…
In the field of machine learning, the well-trained model is assumed to be able to recover the training labels, i.e. the synthetic labels predicted by the model should be as close to the ground-truth labels as possible. Inspired by this, we…
Recent work on multilingual neural machine translation reported competitive performance with respect to bilingual models and surprisingly good performance even on (zeroshot) translation directions not observed at training time. We…
Fine-tuning pre-trained Neural Machine Translation (NMT) models is the dominant approach for adapting to new languages and domains. However, fine-tuning requires adapting and maintaining a separate model for each target task. We propose a…
Over the last few years two promising research directions in low-resource neural machine translation (NMT) have emerged. The first focuses on utilizing high-resource languages to improve the quality of low-resource languages via…
Multilingual machine translation (MMT), trained on a mixture of parallel and monolingual data, is key for improving translation in low-resource language pairs. However, the literature offers conflicting results on the performance of…
Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo…
Massively multilingual models for neural machine translation (NMT) are theoretically attractive, but often underperform bilingual models and deliver poor zero-shot translations. In this paper, we explore ways to improve them. We argue that…
Continuously-growing data volumes lead to larger generic models. Specific use-cases are usually left out, since generic models tend to perform poorly in domain-specific cases. Our work addresses this gap with a method for selecting…
Existing data augmentation approaches for neural machine translation (NMT) have predominantly relied on back-translating in-domain (IND) monolingual corpora. These methods suffer from issues associated with a domain information gap, which…
Document-level neural machine translation has yielded attractive improvements. However, majority of existing methods roughly use all context sentences in a fixed scope. They neglect the fact that different source sentences need different…
While machine translation has traditionally relied on large amounts of parallel corpora, a recent research line has managed to train both Neural Machine Translation (NMT) and Statistical Machine Translation (SMT) systems using monolingual…
This paper explores augmenting monolingual data for knowledge distillation in neural machine translation. Source language monolingual text can be incorporated as a forward translation. Interestingly, we find the best way to incorporate…
To mitigate the negative effect of low quality training data on the performance of neural machine translation models, most existing strategies focus on filtering out harmful data before training starts. In this paper, we explore strategies…
Back-translation provides a simple yet effective approach to exploit monolingual corpora in Neural Machine Translation (NMT). Its iterative variant, where two opposite NMT models are jointly trained by alternately using a synthetic parallel…
In this paper, we explore alternative ways to train a neural machine translation system in a multi-domain scenario. We investigate data concatenation (with fine tuning), model stacking (multi-level fine tuning), data selection and…
The machine translation mechanism translates texts automatically between different natural languages, and Neural Machine Translation (NMT) has gained attention for its rational context analysis and fluent translation accuracy. However,…
In recent years, Neural Machine Translation (NMT) has been shown to be more effective than phrase-based statistical methods, thus quickly becoming the state of the art in machine translation (MT). However, NMT systems are limited in…
Multilingual neural machine translation (MNMT) learns to translate multiple language pairs with a single model, potentially improving both the accuracy and the memory-efficiency of deployed models. However, the heavy data imbalance between…
Machine Translation (MT) has been widely used for cross-lingual classification, either by translating the test set into English and running inference with a monolingual model (translate-test), or translating the training set into the target…