Surface Realization Shared Task 2018 (SR18): The Tilburg University Approach
Thiago Castro Ferreira, Sander Wubben, Emiel Krahmer · 2018
This study describes the approach developed by the Tilburg University team to the shallow track of the Multilingual Surface Realization Shared Task 2018 (SR18).Based on Castro Ferreira et al. (2017), the approach works by first preprocessing an input dependency tree into an ordered linearized string, which is then realized using a statistical machine translation model.Our approach shows promising results, with BLEU scores above 40 for 4 different languages in development and test sets (English, French, Italian and Spanish) and above 30 for the Dutch and Portuguese languages.The model is publicly available 1 .