Related papers: Unsupervised Machine Translation Using Monolingual…
An important concern in training multilingual neural machine translation (NMT) is to translate between language pairs unseen during training, i.e zero-shot translation. Improving this ability kills two birds with one stone by providing an…
In neural machine translation (NMT), monolingual data in the target language are usually exploited through a method so-called "back-translation" to synthesize additional training parallel data. The synthetic data have been shown helpful to…
The vast majority of evaluation metrics for machine translation are supervised, i.e., (i) are trained on human scores, (ii) assume the existence of reference translations, or (iii) leverage parallel data. This hinders their applicability to…
It is relatively easy to mine a large parallel corpus for any machine learning task, such as speech-to-text or speech-to-speech translation. Although these mined corpora are large in volume, their quality is questionable. This work shows…
Cross-language learning allows us to use training data from one language to build models for a different language. Many approaches to bilingual learning require that we have word-level alignment of sentences from parallel corpora. In this…
Despite the growing variety of languages supported by existing multilingual neural machine translation (MNMT) models, most of the world's languages are still being left behind. We aim to extend large-scale MNMT models to incorporate a new…
Deep neural networks have achieved great successes on the image captioning task. However, most of the existing models depend heavily on paired image-sentence datasets, which are very expensive to acquire. In this paper, we make the first…
The goal of universal machine translation is to learn to translate between any pair of languages, given a corpus of paired translated documents for \emph{a small subset} of all pairs of languages. Despite impressive empirical results and an…
We present a family of neural-network--inspired models for computing continuous word representations, specifically designed to exploit both monolingual and multilingual text. This framework allows us to perform unsupervised training of…
Multimodal neural machine translation (NMT) has become an increasingly important area of research over the years because additional modalities, such as image data, can provide more context to textual data. Furthermore, the viability of…
We propose multi-way, multilingual neural machine translation. The proposed approach enables a single neural translation model to translate between multiple languages, with a number of parameters that grows only linearly with the number of…
An effective method to generate a large number of parallel sentences for training improved neural machine translation (NMT) systems is the use of back-translations of the target-side monolingual data. Recently, iterative back-translation…
This research article examines the effectiveness of various pretraining strategies for developing machine translation models tailored to low-resource languages. Although this work considers several low-resource languages, including…
Although many context-aware neural machine translation models have been proposed to incorporate contexts in translation, most of those models are trained end-to-end on parallel documents aligned in sentence-level. Because only a few domains…
We present a textless speech-to-speech translation (S2ST) system that can translate speech from one language into another language and can be built without the need of any text data. Different from existing work in the literature, we tackle…
Shared multilingual representations are essential for cross-lingual tasks and knowledge transfer across languages. This study looks at the impact of parallel data, i.e. translated sentences, in pretraining as a signal to trigger…
Most vision-and-language pretraining research focuses on English tasks. However, the creation of multilingual multimodal evaluation datasets (e.g. Multi30K, xGQA, XVNLI, and MaRVL) poses a new challenge in finding high-quality training data…
Resources for the non-English languages are scarce and this paper addresses this problem in the context of machine translation, by automatically extracting parallel sentence pairs from the multilingual articles available on the Internet. In…
We consider the problem of aligning two sets of continuous word representations, corresponding to languages, to a common space in order to infer a bilingual lexicon. It was recently shown that it is possible to infer such lexicon, without…
Recent progress on unsupervised learning of cross-lingual embeddings in bilingual setting has given impetus to learning a shared embedding space for several languages without any supervision. A popular framework to solve the latter problem…