Ten pairs to tag - Multilingual POS tagging via coarse mapping between embeddings
Name
Barzilay_Ten pairs to tag.pdf
Size
264.13 KB
Format
Adobe PDF
Checksum (MD5)
35d7089798278003371f265a30463cbf
Author(s)
Gaddy, David M.
Zhang, Yuan
Barzilay, Regina
Jaakkola, Tommi S.
Date Issued
June 2016
Journal
15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Publisher
Association for Computational Linguistics
Citation
Zhang, Yuan et al. "Ten Pairs to Tag - Multilingual POS Tagging via Course Mapping between Embeddings." 15th Annual Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, San Diego, California, USA, 12-17 June, 2016. Association for Computational Linguistics, 2016.
Version
Author's final manuscript
Abstract
In the absence of annotations in the target language, multilingual models typically draw on extensive parallel resources. In this paper, we
demonstrate that accurate multilingual partof-speech (POS) tagging can be done with just a few (e.g., ten) word translation pairs. We use the translation pairs to establish a coarse linear isometric (orthonormal) mapping between
monolingual embeddings. This enables the supervised source model expressed in terms of embeddings to be used directly on the target language. We further refine the model in an unsupervised manner by initializing and regularizing it to be close to the direct transfer model. Averaged across six languages, our model yields a 37.5% absolute
improvement over the monolingual prototypedriven method (Haghighi and Klein, 2006) when using a comparable amount of supervision. Moreover, to highlight key linguistic characteristics of the generated tags, we use them to predict typological properties of languages, obtaining a 50% error reduction relative to the prototype model
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike
Persistent DSpace Link
DOI of Published Version
http://dblp.dagstuhl.de/db/conf/naacl/naacl2016.html
