LIMSI@CoNLL'17: UD Shared Task
2017-08-01CONLL 2017Unverified0· sign in to hype
Lauriane Aufrant, Guillaume Wisniewski, Fran{\c{c}}ois Yvon
Unverified — Be the first to reproduce this paper.
ReproduceAbstract
This paper describes LIMSI's submission to the CoNLL 2017 UD Shared Task, which is focused on small treebanks, and how to improve low-resourced parsing only by ad hoc combination of multiple views and resources. We present our approach for low-resourced parsing, together with a detailed analysis of the results for each test treebank. We also report extensive analysis experiments on model selection for the PUD treebanks, and on annotation consistency among UD treebanks.