Related papers: Learning to Detect Unacceptable Machine Translatio…
Machine translation is a popular test bed for research in neural sequence-to-sequence models but despite much recent research, there is still a lack of understanding of these models. Practitioners report performance degradation with large…
Despite the reported success of unsupervised machine translation (MT), the field has yet to examine the conditions under which these methods succeed, and where they fail. We conduct an extensive empirical evaluation of unsupervised MT using…
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:…
Recent work has found that multi-task training with a large number of diverse tasks can uniformly improve downstream performance on unseen target tasks. In contrast, literature on task transferability has established that the choice of…
To train neural machine translation models simultaneously on multiple tasks (languages), it is common to sample each task uniformly or in proportion to dataset sizes. As these methods offer little control over performance trade-offs, we…
A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better…
Through the development of neural machine translation, the quality of machine translation systems has been improved significantly. By exploiting advancements in deep learning, systems are now able to better approximate the complex mapping…
Mechanistic interpretability (MI) is an emerging sub-field of interpretability that seeks to understand a neural network model by reverse-engineering its internal computations. Recently, MI has garnered significant attention for…
A multilingual tokenizer is a fundamental component of multilingual neural machine translation. It is trained from a multilingual corpus. Since a skewed data distribution is considered to be harmful, a sampling strategy is usually used to…
A large number of machine translation approaches have recently been developed to facilitate the fluid migration of content across languages. However, the literature suggests that many obstacles must still be dealt with to achieve better…
For the past 60 years, Research in machine translation is going on. For the development in this field, a lot of new techniques are being developed each day. As a result, we have witnessed development of many automatic machine translators. A…
This work introduces a machine translation task where the output is aimed at audiences of different levels of target language proficiency. We collect a high quality dataset of news articles available in English and Spanish, written for…
Recent advances in NLP demonstrate the effectiveness of training large-scale language models and transferring them to downstream tasks. Can fine-tuning these models on tasks other than language modeling further improve performance? In this…
Multilingual machine translation addresses the task of translating between multiple source and target languages. We propose task-specific attention models, a simple but effective technique for improving the quality of sequence-to-sequence…
In recent years, multi-modal machine translation has attracted significant interest in both academia and industry due to its superior performance. It takes both textual and visual modalities as inputs, leveraging visual context to tackle…
Although coherence modeling has come a long way in developing novel models, their evaluation on downstream applications for which they are purportedly developed has largely been neglected. With the advancements made by neural approaches in…
Machine Translation Quality Estimation is a notoriously difficult task, which lessens its usefulness in real-world translation environments. Such scenarios can be improved if quality predictions are accompanied by a measure of uncertainty.…
Modern machine translation (MT) systems depend on large parallel corpora, often collected from the Internet. However, recent evidence indicates that (i) a substantial portion of these texts are machine-generated translations, and (ii) an…
Current speech translation systems, while having achieved impressive accuracies, are rather static in their behavior and do not adapt to real-world situations in ways human interpreters do. In order to improve their practical usefulness and…
Large-scale pre-training followed by downstream fine-tuning is an effective solution for transferring deep-learning-based models. Since finetuning all possible pre-trained models is computational costly, we aim to predict the…