Using Universal Linguistic Knowledge to Guide Grammar Induction
Name
Barzilay_Using universal.pdf
Size
210.04 KB
Format
Adobe PDF
Checksum (MD5)
5f747af1a8b22b14c0589a5dfd11bbd8
Author(s)
Naseem, Tahira
Chen, Harr
Barzilay, Regina
Johnson, Mark
Date Issued
October 2010
Journal
Proceedings of EMNLP 2010: Conference on Empirical Methods in Natural Language Processing
Citation
Naseem, Tahira et al. "Using Universal Linguistic Knowledge to Guide Grammar Induction." Proceedings of EMNLP 2010: Conference on Empirical Methods in Natural Language Processing, October 9-11, 2010, MIT, Massachusetts, USA.
Version
Author's final manuscript
Abstract
We present an approach to grammar induction
that utilizes syntactic universals to improve
dependency parsing across a range of
languages. Our method uses a single set
of manually-specified language-independent
rules that identify syntactic dependencies between
pairs of syntactic categories that commonly
occur across languages. During inference
of the probabilistic model, we use posterior
expectation constraints to require that a
minimum proportion of the dependencies we
infer be instances of these rules. We also automatically
refine the syntactic categories given
in our coarsely tagged input. Across six languages
our approach outperforms state-of-the-art
unsupervised methods by a significant margin.
Description
URL to papers list on conference site
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 3.0
Persistent DSpace Link
DOI of Published Version
http://www.lsi.upc.edu/events/emnlp2010/papers.html
