We present a survey covering the state of the art in low-resource machine translation (MT)
research. There are currently around 7,000 languages spoken in the world and almost all …

We present Samanantar, the largest publicly available parallel corpora collection for Indic
languages. The collection contains a total of 49.7 million sentence pairs between English …

Hallucinations and off-target translation remain unsolved problems in machine translation,
especially for low-resource languages and massively multilingual models. In this paper, we …

Few-shot crosslingual transfer has been shown to outperform its zero-shot counterpart with
pretrained encoders like multilingual BERT. Despite its growing popularity, little to no …

Multilingual neural machine translation has shown the capability of directly translating
between language pairs unseen in training, ie zero-shot translation. Despite being …

In a multilingual neural machine translation model that fully shares parameters across all
languages, an artificial language token is usually used to guide translation into the desired …

Zero-shot translations is a fascinating feature of Multilingual Neural Machine Translation
(MNMT) systems. These MNMT models are usually trained on English-centric data, ie …

Multilingual neural machine translation can translate unseen language pairs during training,
ie zero-shot translation. However, the zero-shot translation is always unstable. Although …

This paper proposes a simple yet effective method to improve direct (X-to-Y) translation for
both cases: zero-shot and when direct data is available. We modify the input tokens at both …

Multilingual Neural Machine Translation has been showing great success using transformer
models. Deploying these models is challenging because they usually require large …