Related papers: Iterative Batch Back-Translation for Neural Machin…
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…
Neural machine translation is known to require large numbers of parallel training sentences, which generally prevent it from excelling on low-resource language pairs. This thesis explores the use of cross-lingual transfer learning on neural…
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.…
Parallel corpora are indispensable for training neural machine translation (NMT) models, and parallel corpora for most language pairs do not exist or are scarce. In such cases, pivot language NMT can be helpful where a pivot language is…
While achieving state-of-the-art results in multiple tasks and languages, translation-based cross-lingual transfer is often overlooked in favour of massively multilingual pre-trained encoders. Arguably, this is due to its main limitations:…
Neural Machine Translation (NMT) has been proven to achieve impressive results. The NMT system translation results depend strongly on the size and quality of parallel corpora. Nevertheless, for many language pairs, no rich-resource parallel…
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…
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…
Recently, numbers of works shows that the performance of neural machine translation (NMT) can be improved to a certain extent with using visual information. However, most of these conclusions are drawn from the analysis of experimental…
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…
Language models (LMs) pretrained on a large text corpus and fine-tuned on a downstream text corpus and fine-tuned on a downstream task becomes a de facto training strategy for several natural language processing (NLP) tasks. Recently, an…
Recent works have shown that synthetic parallel data automatically generated by translation models can be effective for various neural machine translation (NMT) issues. In this study, we build NMT systems using only synthetic parallel data.…
Context-aware neural machine translation (NMT) is a promising direction to improve the translation quality by making use of the additional context, e.g., document-level translation, or having meta-information. Although there exist various…
Despite the fact that multilingual agreement (MA) has shown its importance for multilingual neural machine translation (MNMT), current methodologies in the field have two shortages: (i) require parallel data between multiple language pairs,…
Multilingual Neural Machine Translation approaches are based on the use of task-specific models and the addition of one more language can only be done by retraining the whole system. In this work, we propose a new training schedule that…
Neural Machine Translation (NMT) systems rely on large amounts of parallel data. This is a major challenge for low-resource languages. Building on recent work on unsupervised and semi-supervised methods, we present an approach that combines…
While recent neural machine translation approaches have delivered state-of-the-art performance for resource-rich language pairs, they suffer from the data scarcity problem for resource-scarce language pairs. Although this problem can be…
We aim to better exploit the limited amounts of parallel text available in low-resource settings by introducing a differentiable reconstruction loss for neural machine translation (NMT). This loss compares original inputs to reconstructed…
Multilingual Neural Machine Translation (MNMT) models are commonly trained on a joint set of bilingual corpora which is acutely English-centric (i.e. English either as the source or target language). While direct data between two languages…
We consider the problem of learning general-purpose, paraphrastic sentence embeddings in the setting of Wieting et al. (2016b). We use neural machine translation to generate sentential paraphrases via back-translation of bilingual sentence…