Related papers: Guided Alignment Training for Topic-Aware Neural M…
Neural Machine Translation (NMT) approaches employing monolingual data are showing steady improvements in resource rich conditions. However, evaluations using real-world low-resource languages still result in unsatisfactory performance.…
Most state-of-the-art neural machine translation systems, despite being different in architectural skeletons (e.g. recurrence, convolutional), share an indispensable feature: the Attention. However, most existing attention methods are…
The principal task in supervised neural machine translation (NMT) is to learn to generate target sentences conditioned on the source inputs from a set of parallel sentence pairs, and thus produce a model capable of generalizing to unseen…
While most neural machine translation (NMT) systems are still trained using maximum likelihood estimation, recent work has demonstrated that optimizing systems to directly improve evaluation metrics such as BLEU can substantially improve…
Neural Machine Translation (NMT) models are typically trained on heterogeneous data that are concatenated and randomly shuffled. However, not all of the training data are equally useful to the model. Curriculum training aims to present the…
Document-level machine translation incorporates inter-sentential dependencies into the translation of a source sentence. In this paper, we propose a new framework to model cross-sentence dependencies by training neural machine translation…
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…
Recent literature has demonstrated the potential of multilingual Neural Machine Translation (mNMT) models. However, the most efficient models are not well suited to specialized industries. In these cases, internal data is scarce and…
Scarcity of parallel sentence-pairs poses a significant hurdle for training high-quality Neural Machine Translation (NMT) models in bilingually low-resource scenarios. A standard approach is transfer learning, which involves taking a model…
With the rapid advancement of Neural Machine Translation (NMT), enhancing translation efficiency and quality has become a focal point of research. Despite the commendable performance of general models such as the Transformer in various…
Back-translation has proven to be an effective method to utilize monolingual data in neural machine translation (NMT), and iteratively conducting back-translation can further improve the model performance. Selecting which monolingual data…
When training multilingual machine translation (MT) models that can translate to/from multiple languages, we are faced with imbalanced training sets: some languages have much more training data than others. Standard practice is to up-sample…
In translation, considering the document as a whole can help to resolve ambiguities and inconsistencies. In this paper, we propose a cross-sentence context-aware approach and investigate the influence of historical contextual information on…
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…
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…
Monolingual data have been demonstrated to be helpful in improving translation quality of both statistical machine translation (SMT) systems and neural machine translation (NMT) systems, especially in resource-poor or domain adaptation…
Translation-tailored Large language models (LLMs) exhibit remarkable translation capabilities, even competing with supervised-trained commercial translation systems. However, off-target translation remains an unsolved problem, especially…
Intelligent selection of training data has proven a successful technique to simultaneously increase training efficiency and translation performance for phrase-based machine translation (PBMT). With the recent increase in popularity of…
Although attention-based Neural Machine Translation (NMT) has achieved remarkable progress in recent years, it still suffers from issues of repeating and dropping translations. To alleviate these issues, we propose a novel key-value…
We propose a neural machine translation (NMT) approach that, instead of pursuing adequacy and fluency ("human-oriented" quality criteria), aims to generate translations that are best suited as input to a natural language processing…