Abstract
This paper describes Fudan's submission to CoNLL 2018's shared task Universal Dependency Parsing. We jointly train models when two languages are similar according to linguistic typology and then do an ensemble of the models using a simple re-parse algorithm. Our system outperforms the baseline method by 4.4% and 2.1% on the development and test set of CoNLL 2018 UD Shared Task, separately.1. Our code is available on https://github.com/taineleau/FudanParser.
Cite
CITATION STYLE
Chen, D., Lin, M., Hu, Z., & Qiu, X. (2018). A simple yet effective joint training method for cross-lingual universal dependency parsing. In CoNLL 2018 - SIGNLL Conference on Computational Natural Language Learning, Proceedings of the CoNLL 2018 Shared Task: Multilingual Parsing from Raw Text to Universal Dependencies (pp. 256–263). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/K18-2026
Register to see more suggestions
Mendeley helps you to discover research relevant for your work.
