Multilingual Neural Architectures for Natural Language Processing

Starting: 01/09/2016
PhD Student: Adrien Bardet
Advisor(s): Sylvain Meignier (LIUM, LST)
Co-advisor(s): Loïc Barrault (LIUM, LST) & Fethi Bougares (LIUM, LST)
Funding: M2CR

The objective of this thesis is machine translation through multilingual neural systems. The effectiveness of these approaches as already been shown in monolingual machine translation where you translate from a single source language to a single target language. On the other hand multilingual neural machine translation where you translate from multiple source languages to multiple target languages has been barely studied compared to other approaches, despite its relevance shown in different papers.