Climbing the tower of babel: Unsupervised multilingual learning

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, su...

Full description

Bibliographic Details
Main Authors: Snyder, Benjamin, Barzilay, Regina
Other Authors: Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Format: Article
Language:en_US
Published: Omnipress 2011
Online Access:http://hdl.handle.net/1721.1/61698
https://orcid.org/0000-0002-2921-8201
_version_ 1826209096050671616
author Snyder, Benjamin
Barzilay, Regina
author2 Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
author_facet Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Snyder, Benjamin
Barzilay, Regina
author_sort Snyder, Benjamin
collection MIT
description 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.
first_indexed 2024-09-23T14:17:12Z
format Article
id mit-1721.1/61698
institution Massachusetts Institute of Technology
language en_US
last_indexed 2024-09-23T14:17:12Z
publishDate 2011
publisher Omnipress
record_format dspace
spelling mit-1721.1/616982022-09-28T19:45:48Z Climbing the tower of babel: Unsupervised multilingual learning Snyder, Benjamin Barzilay, Regina Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory Massachusetts Institute of Technology. Department of Electrical Engineering and Computer Science Barzilay, Regina Snyder, Benjamin Barzilay, Regina 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. 2011-03-15T13:23:56Z 2011-03-15T13:23:56Z 2010-06 2010-06 Article http://purl.org/eprint/type/ConferencePaper 978-1-60558-907-7 http://hdl.handle.net/1721.1/61698 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. https://orcid.org/0000-0002-2921-8201 en_US http://www.icml2010.org/papers/905.pdf Proceedings of the 27th International Conference on Machine Learning (ICML-10) 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. application/pdf Omnipress MIT web domain
spellingShingle Snyder, Benjamin
Barzilay, Regina
Climbing the tower of babel: Unsupervised multilingual learning
title Climbing the tower of babel: Unsupervised multilingual learning
title_full Climbing the tower of babel: Unsupervised multilingual learning
title_fullStr Climbing the tower of babel: Unsupervised multilingual learning
title_full_unstemmed Climbing the tower of babel: Unsupervised multilingual learning
title_short Climbing the tower of babel: Unsupervised multilingual learning
title_sort climbing the tower of babel unsupervised multilingual learning
url http://hdl.handle.net/1721.1/61698
https://orcid.org/0000-0002-2921-8201
work_keys_str_mv AT snyderbenjamin climbingthetowerofbabelunsupervisedmultilinguallearning
AT barzilayregina climbingthetowerofbabelunsupervisedmultilinguallearning