NAACL 2019

The Sixth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2019) has been accepted to be part of NAACL 2019.

FoTran is involved in the organisation.

 

Recent activities in FoTran

The FoTran project’s recent activities in Finland and abroad

Jörg Tiedemann took part in a panel at the ELRC workshop organised by FIN-CLARIN in October 2018. Video of the panel session: https://youtu.be/1QEKcHUwY3I 

A workshop on Data Curation for (Neural) Machine Translation was organised by Tiedemann in Luxembourg.

Alessandro Raganato, Raul Vazquez and Jörg Tiedemann gave a short talk and presented a poster about FoTran in December 2018 at AI day at Aalto.

 

FoTran project at DHN 2018

Jörg Tiedemann presented some early ideas and experiments related to the FoTran project at the recent DHN 2018 conference in Helsinki.

Jörg Tiedemann presenting his paper “Emerging Language Spaces Learned From Massively Multilingual Corpora” at DHN 2018

Emerging Language Spaces Learned From Massively Multilingual Corpora

Abstract:
Translations capture important information about languages that can be used as implicit supervision in learning linguistic properties and semantic representations. In an information-centric view, translated texts may be considered as semantic mirrors of the original text and the significant variations that we can observe across various languages can be used to disambiguate a given expression using the linguistic signal that is grounded in translation. Parallel corpora consisting of massive amounts of human translations with a large linguistic variation can be applied to increase abstractions and we propose the use of highly multilingual machine translation models to find language-independent meaning representations. Our initial experiments show that neural machine translation models can indeed learn in such a setup and we can show that the learning algorithm picks up information about the relation between languages in order to optimize transfer leaning with shared parameters. The model creates a continuous language space that represents relationships in terms of geometric distances, which we can visualize to illustrate how languages cluster according to language families and groups. Does this open the door for new ideas of data-driven language typology with promising models and techniques in empirical cross-linguistic research?

Download the full paper: [pdf]

We’re hiring!

The FoTran project will officially start in spring 2018. We are currently looking for motivated people with a background in computational linguistics or computer science to join our team. Please, get in touch with us (via e-mail to jorg.tiedemann at helsinki.fi) if you are interested in doing your post-doctoral research or a PhD within the scope of the project!

Welcome

Welcome to the FoTran project website. We are just setting up the site so more information will be added shortly.