82 Treebanks, 34 models: Universal dependency parsing with multi-treebank models

47Citations
Citations of this article
72Readers
Mendeley users who have this article in their library.

Abstract

We present the Uppsala system for the CoNLL 2018 Shared Task on universal dependency parsing. Our system is a pipeline consisting of three components: the first performs joint word and sentence segmentation; the second predicts part-of-speech tags and morphological features; the third predicts dependency trees from words and tags. Instead of training a single parsing model for each treebank, we trained models with multiple treebanks for one language or closely related languages, greatly reducing the number of models. On the official test run, we ranked 7th of 27 teams for the LAS and MLAS metrics. Our system obtained the best scores overall for word segmentation, universal POS tagging, and morphological features.

Cite

CITATION STYLE

APA

Smith, A., Bohnet, B., De Lhoneux, M., Nivre, J., Shao, Y., & Stymne, S. (2018). 82 Treebanks, 34 models: Universal dependency parsing with multi-treebank models. 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. 113–123). Association for Computational Linguistics (ACL). https://doi.org/10.18653/v1/K18-2011

Register to see more suggestions

Mendeley helps you to discover research relevant for your work.

Already have an account?

Save time finding and organizing research with Mendeley

Sign up for free