Related papers: A Universal Parent Model for Low-Resource Neural M…
Pre-trained models have demonstrated their effectiveness in many downstream natural language processing (NLP) tasks. The availability of multilingual pre-trained models enables zero-shot transfer of NLP tasks from high resource languages to…
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…
Differently from the traditional statistical MT that decomposes the translation task into distinct separately learned components, neural machine translation uses a single neural network to model the entire translation process. Despite…
When the amount of parallel sentences available to train a neural machine translation is scarce, a common practice is to generate new synthetic training samples from them. A number of approaches have been proposed to produce synthetic…
Even for common NLP tasks, sufficient supervision is not available in many languages -- morphological tagging is no exception. In the work presented here, we explore a transfer learning scheme, whereby we train character-level recurrent…
Scarcity of parallel sentence pairs is a major challenge for training high quality neural machine translation (NMT) models in bilingually low-resource scenarios, as NMT is data-hungry. Multi-task learning is an elegant approach to inject…
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…
Using a language model (LM) pretrained on two languages with large monolingual data in order to initialize an unsupervised neural machine translation (UNMT) system yields state-of-the-art results. When limited data is available for one…
We describe a cross-lingual transfer method for dependency parsing that takes into account the problem of word order differences between source and target languages. Our model only relies on the Bible, a considerably smaller parallel data…
Program translation is an important tool to migrate legacy code in one language into an ecosystem built in a different language. In this work, we are the first to employ deep neural networks toward tackling this problem. We observe that…
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:…
End-to-end text-to-speech (TTS) has shown great success on large quantities of paired text plus speech data. However, laborious data collection remains difficult for at least 95% of the languages over the world, which hinders the…
State-of-the-art machine translation (MT) systems are typically trained to generate the "standard" target language; however, many languages have multiple varieties (regional varieties, dialects, sociolects, non-native varieties) that are…
Neural machine translation, a recently proposed approach to machine translation based purely on neural networks, has shown promising results compared to the existing approaches such as phrase-based statistical machine translation. Despite…
Recent speech technologies have led to produce high quality synthesised speech due to recent advances in neural Text to Speech (TTS). However, such TTS models depend on extensive amounts of data that can be costly to produce and is hardly…
Modern Neural Machine Translation systems exhibit strong performance in several different languages and are constantly improving. Their ability to learn continuously is, however, still severely limited by the catastrophic forgetting issue.…
Recent advances in neural TTS have led to models that can produce high-quality synthetic speech. However, these models typically require large amounts of training data, which can make it costly to produce a new voice with the desired…
In many humanitarian scenarios, translation into severely low resource languages often does not require a universal translation engine, but a dedicated text-specific translation engine. For example, healthcare records, hygienic procedures,…
Neural machine translation systems require large amounts of training data and resources. Even with this, the quality of the translations may be insufficient for some users or domains. In such cases, the output of the system must be revised…
Common intermediate language representation in neural machine translation can be used to extend bilingual to multilingual systems by incremental training. In this paper, we propose a new architecture based on introducing an interlingual…