The DipInfo-UniTo system for SRST 2018

Abstract

This paper describes the system developed by the DipInfo-UniTo team to participate to the shallow track of the Surface Realization Shared Task 2018 (Mille et al., 2018). The system employs two separate neural networks with different architectures to predict the word ordering and the morphological inflection independently from each other. The UniTo realizer is language independent, and its simple architecture allowed it to be scored in the central part of the final ranking of the shared task.

Surface Realisation Using Full Delexicalisation

“…For word ordering, five teams chose an approach based on neural networks, two used a classifier, and one team resorted to a language model. As for the inflection subtask, five teams applied neural techniques, two used lexicon-based approaches, and one used an SMT system (Basile and Mazzei, 2018;Castro Ferreira et al, 2018;Elder and Hokamp, 2018;King and White, 2018;Madsack et al, 2018;Puzikov and Gurevych, 2018;Singh et al, 2018;Sobrevilla Cabezudo and Pardo, 2018). Overall, neural components were dominant across all the participants.…”

Weighted posets: Learning surface order from dependency trees

“…Gómez-Rodríguez, 2016). Similarly, the submissions to SR '18 vary with regard to projectivity: of the eight, three explicitly exclude non-projective arcs due to algorithmic design (Basile and Mazzei, 2018;Puzikov and Gurevych, 2018;Sobrevilla Cabezudo and Pardo, 2018), while one follows the tendency toward limited non-projectivity by "encourag[ing] the model to learn that most choices should yield continuous phrases" (King and White, 2018, p. 42).…”

Proceedings of the 18th International Workshop on Treebanks and Linguistic Theories (TLT, SyntaxFest 2019)

“…Gómez-Rodríguez, 2016). Similarly, the submissions to SR '18 vary with regard to projectivity: of the eight, three explicitly exclude non-projective arcs due to algorithmic design (Basile and Mazzei, 2018;Puzikov and Gurevych, 2018;Sobrevilla Cabezudo and Pardo, 2018), while one follows the tendency toward limited non-projectivity by "encourag[ing] the model to learn that most choices should yield continuous phrases" (King and White, 2018, p. 42).…”