Joint part-of-speech and dependency projection from multiple sources

TY - GEN

T1 - Joint part-of-speech and dependency projection from multiple sources

AU - Johannsen, Anders Trærup

AU - Agic, Zeljko

AU - Søgaard, Anders

N1 - Conference code: 54

PY - 2016

Y1 - 2016

N2 - Most previous work on annotation projection has been limited to a subset of Indo-European languages, using only a single source language, and projecting annotation for one task at a time. In contrast, we present an Integer Linear Programming (ILP) algorithm that simultaneously projects annotation for multiple tasks from multiple source languages, relying on parallel corpora available for hundreds of languages. When training POS taggers and dependency parsers on jointly projected POS tags and syntactic dependencies using our algorithm, we obtain better performance than a standard approach on 20/23 languages using one parallel corpus; and 18/27 languages using another.

AB - Most previous work on annotation projection has been limited to a subset of Indo-European languages, using only a single source language, and projecting annotation for one task at a time. In contrast, we present an Integer Linear Programming (ILP) algorithm that simultaneously projects annotation for multiple tasks from multiple source languages, relying on parallel corpora available for hundreds of languages. When training POS taggers and dependency parsers on jointly projected POS tags and syntactic dependencies using our algorithm, we obtain better performance than a standard approach on 20/23 languages using one parallel corpus; and 18/27 languages using another.

M3 - Article in proceedings

SN - 978-1-945626-01-2

VL - 2 (Short papers)

BT - Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics

PB - Association for Computational Linguistics

T2 - 54th Annual Meeting of the Association for Computational Linguistics

Y2 - 7 August 2016 through 12 August 2016

ER -