Climbing the tower of babel: Unsupervised multilingual learning
Author(s)
Snyder, Benjamin; Barzilay, Regina
DownloadBarzilay_Climbing the.pdf (596.0Kb)
PUBLISHER_POLICY
Publisher Policy
Article is made available in accordance with the publisher's policy and may be subject to US copyright law. Please refer to the publisher's site for terms of use.
Terms of use
Metadata
Show full item recordAbstract
For centuries, scholars have explored the deep
links among human languages. In this paper,
we present a class of probabilistic models
that use these links as a form of naturally
occurring supervision. These models allow
us to substantially improve performance for
core text processing tasks, such as morphological
segmentation, part-of-speech tagging,
and syntactic parsing. Besides these traditional
NLP tasks, we also present a multilingual
model for the computational decipherment
of lost languages.
Date issued
2010-06Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory; Massachusetts Institute of Technology. Department of Electrical Engineering and Computer ScienceJournal
Proceedings of the 27th International Conference on Machine Learning (ICML-10)
Publisher
Omnipress
Citation
Snyder, Benjamin, and Regina Barzilay. “Climbing the Tower of Babel: Unsupervised Multilingual Learning.” Proceedings of the 27th International Conference on Machine Learning (ICML-10). Haifa, Israel:29-36.
Version: Author's final manuscript
ISBN
978-1-60558-907-7