no code implementations • LT4HALA (LREC) 2022 • Mathieu Dehouck
In this paper, we introduce the first dependency treebank for the Umbrian language (an extinct Indo-European language from the Italic family, once spoken in modern day Italy).
no code implementations • ACL (IWPT) 2021 • Mark Anderson, Mathieu Dehouck, Carlos Gómez Rodríguez
We evaluate the efficacy of predicted UPOS tags as input features for dependency parsers in lower resource settings to evaluate how treebank size affects the impact tagging accuracy has on parsing performance.
no code implementations • COLING 2020 • Mathieu Dehouck, Carlos G{\'o}mez-Rodr{\'\i}guez
The lack of annotated data is a big issue for building reliable NLP systems for most of the world{'}s languages.
no code implementations • WS 2020 • Mathieu Dehouck, Mark Anderson, Carlos Gómez-Rodríguez
We present the system submission from the FASTPARSE team for the EUD Shared Task at IWPT 2020.
no code implementations • NAACL 2019 • Mathieu Dehouck, Pascal Denis
Languages evolve and diverge over time.
no code implementations • EMNLP 2018 • Mathieu Dehouck, Pascal Denis
This paper presents a simple framework for characterizing morphological complexity and how it encodes syntactic information.
no code implementations • EACL 2017 • Mathieu Dehouck, Pascal Denis
This paper presents a new approach to the problem of cross-lingual dependency parsing, aiming at leveraging training data from different source languages to learn a parser in a target language.