RACAI’s Natural Language Processing pipeline for Universal Dependencies

Stefan Daniel Dumitrescu, Tiberiu Boros, Dan Tufis


Abstract
This paper presents RACAI’s approach, experiments and results at CONLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies. We handle raw text and we cover tokenization, sentence splitting, word segmentation, tagging, lemmatization and parsing. All results are reported under strict training, development and testing conditions, in which the corpora provided for the shared tasks is used “as is”, without any modifications to the composition of the train and development sets.
Anthology ID:
K17-3018
Volume:
Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Jan Hajič, Dan Zeman
Venue:
CoNLL
SIG:
SIGNLL
Publisher:
Association for Computational Linguistics
Note:
Pages:
174–181
Language:
URL:
https://aclanthology.org/K17-3018
DOI:
10.18653/v1/K17-3018
Bibkey:
Cite (ACL):
Stefan Daniel Dumitrescu, Tiberiu Boros, and Dan Tufis. 2017. RACAI’s Natural Language Processing pipeline for Universal Dependencies. In Proceedings of the CoNLL 2017 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies, pages 174–181, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
RACAI’s Natural Language Processing pipeline for Universal Dependencies (Dumitrescu et al., CoNLL 2017)
Copy Citation:
PDF:
https://aclanthology.org/K17-3018.pdf