Related papers: High-Quality Data Augmentation for Low-Resource NM…

In the current machine translation (MT) landscape, the Transformer architecture stands out as the gold standard, especially for high-resource language pairs. This research delves into its efficacy for low-resource language pairs including…

Backtranslation BT is widely used in low resource machine translation MT to generate additional synthetic training data using monolingual corpora. While this approach has shown strong improvements for many language pairs, its effectiveness…

Back translation (BT) has been widely used and become one of standard techniques for data augmentation in Neural Machine Translation (NMT), BT has proven to be helpful for improving the performance of translation effectively, especially for…

Neural Machine Translation (NMT) models are known to suffer from noisy inputs. To make models robust, we generate adversarial augmentation samples that attack the model and preserve the source-side semantic meaning at the same time. To…

The last decade has witnessed enormous improvements in science and technology, stimulating the growing demand for economic and cultural exchanges in various countries. Building a neural machine translation (NMT) system has become an urgent…

The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves…

With the advent of the Transformer architecture, Neural Machine Translation (NMT) results have shown great improvement lately. However, results in low-resource conditions still lag behind in both bilingual and multilingual setups, due to…

Non-autoregressive (NAR) generation, which is first proposed in neural machine translation (NMT) to speed up inference, has attracted much attention in both machine learning and natural language processing communities. While NAR generation…

Neural Machine Translation (NMT) systems built on multilingual sequence-to-sequence Language Models (msLMs) fail to deliver expected results when the amount of parallel data for a language, as well as the language's representation in the…

Compared with only using limited authentic parallel data as training corpus, many studies have proved that incorporating synthetic parallel data, which generated by back translation (BT) or forward translation (FT, or selftraining), into…

Neural machine translation (NMT) generates the next target token given as input the previous ground truth target tokens during training while the previous generated target tokens during inference, which causes discrepancy between training…

One of the significant challenges of Machine Translation (MT) is the scarcity of large amounts of data, mainly parallel sentence aligned corpora. If the evaluation is as rigorous as resource-rich languages, both Neural Machine Translation…

Machine Translation has made impressive progress in recent years offering close to human-level performance on many languages, but studies have primarily focused on high-resource languages with broad online presence and resources. With the…

The state of art natural language processing systems relies on sizable training datasets to achieve high performance. Lack of such datasets in the specialized low resource domains lead to suboptimal performance. In this work, we adapt…

Prior works have demonstrated that a low-resource language pair can benefit from multilingual machine translation (MT) systems, which rely on many language pairs' joint training. This paper proposes two simple strategies to address the rare…

Reinforcement learning (RL) is frequently used to increase performance in text generation tasks, including machine translation (MT), notably through the use of Minimum Risk Training (MRT) and Generative Adversarial Networks (GAN). However,…

Multilingual neural machine translation (MNMT) trained in multiple language pairs has attracted considerable attention due to fewer model parameters and lower training costs by sharing knowledge among multiple languages. Nonetheless,…

Neural machine translation~(NMT) is ineffective for zero-resource languages. Recent works exploring the possibility of unsupervised neural machine translation (UNMT) with only monolingual data can achieve promising results. However, there…

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…

Back-translation (BT) has become one of the de facto components in unsupervised neural machine translation (UNMT), and it explicitly makes UNMT have translation ability. However, all the pseudo bi-texts generated by BT are treated equally…