A Bayesian model for joint word alignment and part-of-speech transfer

Show full item record



Permalink

http://hdl.handle.net/10138/174276

Citation

Östling , R 2016 , A Bayesian model for joint word alignment and part-of-speech transfer . in Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers . Proceedings of COLING , The Association for Computational Linguistics , Osaka, Japan , pp. 620-629 . < http://coling2016.anlp.jp/#proceedings >

Title: A Bayesian model for joint word alignment and part-of-speech transfer
Author: Östling, Robert
Contributor: University of Helsinki, Department of Modern Languages 2010-2017
Publisher: The Association for Computational Linguistics
Date: 2016-12-01
Language: eng
Number of pages: 10
Belongs to series: Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers
Belongs to series: Proceedings of COLING
ISBN: 978-4-87974-702-0
URI: http://hdl.handle.net/10138/174276
Abstract: Current methods for word alignment require considerable amounts of parallel text to deliver accurate results, a requirement which is met only for a small minority of the world's approximately 7,000 languages. We show that by jointly performing word alignment and annotation transfer in a novel Bayesian model, alignment accuracy can be improved for language pairs where annotations are available for only one of the languages---a finding which could facilitate the study and processing of a vast number of low-resource languages. We also present an evaluation where our method is used to perform single-source and multi-source part-of-speech transfer with 22 translations of the same text in four different languages. This allows us to quantify the considerable variation in accuracy depending on the specific source text(s) used, even with different translations into the same language.
Subject: 6121 Languages
Rights:


Files in this item

Total number of downloads: Loading...

Files Size Format View
coling2016.pdf 240.3Kb PDF View/Open

This item appears in the following Collection(s)

Show full item record