1 code implementation • COLING 2018 • Gongbo Tang, Fabienne Cap, Eva Pettersson, Joakim Nivre
In this paper, we apply different NMT models to the problem of historical spelling normalization for five languages: English, German, Hungarian, Icelandic, and Swedish.
no code implementations • WS 2017 • Sara Stymne, Sharid Lo{\'a}iciga, Fabienne Cap
We describe the Uppsala system for the 2017 DiscoMT shared task on cross-lingual pronoun prediction.
no code implementations • WS 2017 • Rebeca Padilla L{\'o}pez, Fabienne Cap
In this work, we present a first attempt to investigate multi-emoji expressions and whether they behave similarly to multiword expressions in terms of non-compositionality.
no code implementations • WS 2017 • Agata Savary, Carlos Ramisch, Silvio Cordeiro, Federico Sangati, Veronika Vincze, Behrang Qasemizadeh, C, Marie ito, Fabienne Cap, Voula Giouli, Ivelina Stoyanova, Antoine Doucet
This paper presents the corpus annotation methodology and outcome, the shared task organisation and the results of the participating systems.
no code implementations • WS 2017 • Fabienne Cap
We use word alignment variance as an indicator for the non-compositionality of German and English noun compounds.