Existing work in translation demonstrated the potential of massively multilingual machine
translation by training a single model able to translate between any pair of languages …

Abstract Machine translation (MT) technology has facilitated our daily tasks by providing
accessible shortcuts for gathering, processing, and communicating information. However, it …

Is bias amplified when neural machine translation (NMT) models are optimized for speed
and evaluated on generic test sets using BLEU? We investigate architectures and …

Lexical disambiguation is a major challenge for machine translation systems, especially if
some senses of a word are trained less often than others. Identifying patterns of …

We introduce a multilingual extension of the HOLISTICBIAS dataset, the largest English
template-based taxonomy of textual people references: MULTILINGUALHOLISTICBIAS. This …

In many online markets we “shop alone”—there is no way for us to know the prices other
consumers paid for the same goods. Could this lack of price transparency lead to differential …

Recent advancements in natural language processing (NLP) have catalyzed the
development of models capable of generating coherent and contextually relevant …

Pre-training models with large crawled corpora can lead to issues such as toxicity and bias,
as well as copyright and privacy concerns. A promising way of alleviating such concerns is …

This thesis aims to study different language-specific approaches for Multilingual Machine
Translation without parameter sharing and their properties compared to the current state-of …

This paper aims at identifying the information flow in state-of-the-art machine translation
systems, taking as example the transfer of gender when translating from French into English …