A4 Refereed article in a conference publication
Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task
Authors: Jenna Kanerva, Filip Ginter, Sampo Pyysalo
Editors: Gosse Bouma, Yuji Matsumoto, Stephan Oepen, Kenji Sagae, Djamé Seddah, Weiwei Sun, Anders Søgaard, Reut Tsarfaty, Dan Zeman
Conference name: International Conference on Parsing Technologies
Publication year: 2020
Journal: Annual Meeting of the Association for Computational Linguistics
Book title : Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
First page : 162
Last page: 173
Number of pages: 12
ISBN: 978-1-952148-11-8
DOI: https://doi.org/10.18653/v1/2020.iwpt-1.17
Web address : https://www.aclweb.org/anthology/2020.iwpt-1.17
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/50410770
We present the approach of the TurkuNLP group to the IWPT 2020 shared task on Multilingual Parsing into Enhanced Universal Dependencies. The task involves 28 treebanks in 17 different languages and requires parsers to generate graph structures extending on the basic dependency trees. Our approach combines language-specific BERT models, the UDify parser, neural sequence-to-sequence lemmatization and a graph transformation approach encoding the enhanced structure into a dependency tree. Our submission averaged 84.5% ELAS, ranking first in the shared task.
Downloadable publication This is an electronic reprint of the original article. |  |
