Elie Duthoo


pdf bib
CEA LIST: Processing Low-Resource Languages for CoNLL 2018
Elie Duthoo | Olivier Mesnard
Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies

In this paper, we describe the system used for our first participation at the CoNLL 2018 shared task. The submitted system largely reused the state of the art parser from CoNLL 2017 (https://github.com/tdozat/Parser-v2). We enhanced this system for morphological features predictions, and we used all available resources to provide accurate models for low-resource languages. We ranked 5th of 27 participants in MLAS for building morphology aware dependency trees, 2nd for morphological features only, and 3rd for tagging (UPOS) and parsing (LAS) low-resource languages.