Simple Type-Level Unsupervised POS Tagging
Name
Barzilay_Simple type.pdf
Size
393.27 KB
Format
Adobe PDF
Checksum (MD5)
965165205700fb898fa015621c1bb47d
Author(s)
Lee, Yoong Keok
Haghighi, Aria
Barzilay, Regina
Date Issued
October 2010
Journal
Proceedings of the Conference on Empirical Methods in Natural Language Processing, EMNLP 2010
Citation
Lee, Yoong Keok, Aria Haghighi and Regina Barzilay. "Simple Type-Level Unsupervised POS Tagging." in Proceedings of the EMNLP 2010: Conference on Empirical Methods in Natural Language Processing, Oct. 9-11, 2010, MIT, Massachusetts, USA.
Version
Author's final manuscript
Abstract
Part-of-speech (POS) tag distributions are
known to exhibit sparsity — a word is likely
to take a single predominant tag in a corpus.
Recent research has demonstrated that incorporating
this sparsity constraint improves tagging
accuracy. However, in existing systems,
this expansion come with a steep increase in
model complexity. This paper proposes a simple
and effective tagging method that directly
models tag sparsity and other distributional
properties of valid POS tag assignments. In
addition, this formulation results in a dramatic
reduction in the number of model parameters
thereby, enabling unusually rapid training.
Our experiments consistently demonstrate that
this model architecture yields substantial performance
gains over more complex tagging
counterparts. On several languages, we report
performance exceeding that of more complex
state-of-the art systems.
MIT Department
Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory
Terms of Use
Creative Commons Attribution-Noncommercial-Share Alike 3.0
Persistent DSpace Link
DOI of Published Version
http://www.lsi.upc.edu/events/emnlp2010/papers.html
