A4 Vertaisarvioitu artikkeli konferenssijulkaisussa
Turku Enhanced Parser Pipeline: From Raw Text to Enhanced Graphs in the IWPT 2020 Shared Task
Tekijät: Jenna Kanerva, Filip Ginter, Sampo Pyysalo
Toimittaja: Gosse Bouma, Yuji Matsumoto, Stephan Oepen, Kenji Sagae, Djamé Seddah, Weiwei Sun, Anders Søgaard, Reut Tsarfaty, Dan Zeman
Konferenssin vakiintunut nimi: International Conference on Parsing Technologies
Julkaisuvuosi: 2020
Journal: Annual Meeting of the Association for Computational Linguistics
Kokoomateoksen nimi: Proceedings of the 16th International Conference on Parsing Technologies and the IWPT 2020 Shared Task on Parsing into Enhanced Universal Dependencies
Aloitussivu: 162
Lopetussivu: 173
Sivujen määrä: 12
ISBN: 978-1-952148-11-8
DOI: https://doi.org/10.18653/v1/2020.iwpt-1.17
Verkko-osoite: https://www.aclweb.org/anthology/2020.iwpt-1.17
Rinnakkaistallenteen osoite: 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.
Ladattava julkaisu This is an electronic reprint of the original article. |  |
