Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees
Name
Barzilay_Steps to.pdf
Size
447.75 KB
Format
Adobe PDF
Checksum (MD5)
153ae418d74a2879eb011271eb88f5ab
Author(s)
Zhang, Yuan
Lei, Tao
Barzilay, Regina
Jaakkola, Tommi S.
Globerson, Amir
Date Issued
June 2014
Journal
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Citation
Zhang, Yuan, Tao Lei, Regina Barzilay, Tommi Jaakkola, and Amir Globerson. "Steps to Excellence: Simple Inference with Refined Scoring of Dependency Trees." 52nd Annual Meeting of the Association for Computational Linguistics (June 2014).
Version
Author's final manuscript
Abstract
Much of the recent work on dependency parsing has been focused on solving inherent combinatorial problems associated with rich scoring functions. In contrast, we demonstrate that highly expressive scoring functions can be used with substantially simpler inference procedures. Specifically, we introduce a sampling-based parser that can easily handle arbitrary global features. Inspired by SampleRank, we learn to take guided stochastic steps towards a high scoring parse. We introduce two samplers for traversing the space of trees, Gibbs and Metropolis-Hastings with Random Walk. The model outperforms state-of-the-art results when evaluated on 14 languages of non-projective CoNLL datasets. Our sampling-based approach naturally extends to joint prediction scenarios, such as joint parsing and POS correction. The resulting method outperforms the best reported results on the CATiB dataset, approaching performance of parsing with gold tags.
MIT Department
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://acl2014.org/acl2014/P14-1/index.html
