KLcpos3-A language similarity measure for delexicalized parser transfer

32Citations
Citations of this article
90Readers
Mendeley users who have this article in their library.

Abstract

We present KLcpos3, a language similar-ity measure based on Kullback-Leibler di-vergence of coarse part-of-speech tag tri-gram distributions in tagged corpora. It has been designed for multilingual delexi-calized parsing, both for source treebank selection in single-source parser trans-fer, and for source treebank weighting in multi-source transfer. In the selection task, KLcpos3 identifies the best source treebank in 8 out of 18 cases. In the weighting task, it brings +4.5% UAS absolute, compared to unweighted parse tree combination.

Cite

CITATION STYLE

APA

Rosa, R., & Žabokrtský, Z. (2015). KLcpos3-A language similarity measure for delexicalized parser transfer. In ACL-IJCNLP 2015 - 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing of the Asian Federation of Natural Language Processing, Proceedings of the Conference (Vol. 2, pp. 243–249). Association for Computational Linguistics (ACL). https://doi.org/10.3115/v1/p15-2040

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