Related papers: Dynamic Data Selection and Weighting for Iterative…
Existing curriculum learning approaches to Neural Machine Translation (NMT) require sampling sufficient amounts of "easy" samples from training data at the early training stage. This is not always achievable for low-resource languages where…
While neural machine translation (NMT) is making good progress in the past two years, tens of millions of bilingual sentence pairs are needed for its training. However, human labeling is very costly. To tackle this training data bottleneck,…
Recent studies have proven that the training of neural machine translation (NMT) can be facilitated by mimicking the learning process of humans. Nevertheless, achievements of such kind of curriculum learning rely on the quality of…
Modern sentence-level NMT systems often produce plausible translations of isolated sentences. However, when put in context, these translations may end up being inconsistent with each other. We propose a monolingual DocRepair model to…
Multilingual NMT is a viable solution for translating low-resource languages (LRLs) when data from high-resource languages (HRLs) from the same language family is available. However, the training schedule, i.e. the order of presentation of…
Machine translation systems achieve near human-level performance on some languages, yet their effectiveness strongly relies on the availability of large amounts of parallel sentences, which hinders their applicability to the majority of…
Neural machine translation has become the state-of-the-art for language pairs with large parallel corpora. However, the quality of machine translation for low-resource languages leaves much to be desired. There are several approaches to…
Multilingual information retrieval has emerged as powerful tools for expanding knowledge sharing across languages. On the other hand, resources on high quality knowledge base are often scarce and in limited languages, therefore an effective…
Simultaneous machine translation (SiMT) is usually done via sequence-level knowledge distillation (Seq-KD) from a full-sentence neural machine translation (NMT) model. However, there is still a significant performance gap between NMT and…
Large amounts of data has made neural machine translation (NMT) a big success in recent years. But it is still a challenge if we train these models on small-scale corpora. In this case, the way of using data appears to be more important.…
Transfer learning or multilingual model is essential for low-resource neural machine translation (NMT), but the applicability is limited to cognate languages by sharing their vocabularies. This paper shows effective techniques to transfer a…
Word alignment has proven to benefit many-to-many neural machine translation (NMT). However, high-quality ground-truth bilingual dictionaries were used for pre-editing in previous methods, which are unavailable for most language pairs.…
Multilingual Neural Machine Translation (NMT) enables one model to serve all translation directions, including ones that are unseen during training, i.e. zero-shot translation. Despite being theoretically attractive, current models often…
Training efficiency is one of the main problems for Neural Machine Translation (NMT). Deep networks need for very large data as well as many training iterations to achieve state-of-the-art performance. This results in very high computation…
Neural Machine Translation (NMT) models have been proved strong when translating clean texts, but they are very sensitive to noise in the input. Improving NMT models robustness can be seen as a form of "domain" adaption to noise. The…
We present an approach to neural machine translation (NMT) that supports multiple domains in a single model and allows switching between the domains when translating. The core idea is to treat text domains as distinct languages and use…
We explore ways of incorporating bilingual dictionaries to enable semi-supervised neural machine translation. Conventional back-translation methods have shown success in leveraging target side monolingual data. However, since the quality of…
Although the multilingual Neural Machine Translation(NMT), which extends Google's multilingual NMT, has ability to perform zero-shot translation and the iterative self-learning algorithm can improve the quality of zero-shot translation, it…
Machine translation (MT) systems, especially when designed for an industrial setting, are trained with general parallel data derived from the Web. Thus, their style is typically driven by word/structure distribution coming from the average…
In this paper, we explore the effectiveness of combining fine-tuning and backtranslation on a small Japanese corpus for neural machine translation. Starting from a baseline English{\textrightarrow}Japanese model (COMET = 0.460), we first…