Greed Is Good If Randomized: New Inference for Dependency Parsing
Name
Barzilay_Greed is.pdf
Size
333.77 KB
Format
Adobe PDF
Checksum (MD5)
0da4076276e33e7e98e54d92f7600ee9
Author(s)
Zhang, Yuan
Lei, Tao
Barzilay, Regina
Jaakkola, Tommi S.
Date Issued
October 2014
Journal
Proceedings of the 2014 Conference on Empirical Methods on Natural Language Processing
Citation
Zhang, Yuan, Tao Lei, Regina Barzilay, and Tommi Jaakkola. "Greed Is Good If Randomized: New Inference for Dependency Parsing." 2014 Conference on Empirical Methods on Natural Language Processing (October 2014).
Version
Author's final manuscript
Abstract
Dependency parsing with high-order features results in a provably hard decoding problem. A lot of work has gone into developing powerful optimization methods for solving these combinatorial problems. In contrast, we explore, analyze, and demonstrate that a substantially simpler randomized greedy inference algorithm already suffices for near optimal parsing: a) we analytically quantify the number of local optima that the greedy method has to overcome in the context of first-order parsing; b) we show that, as a decoding algorithm, the greedy method surpasses dual decomposition in second-order parsing; c) we empirically demonstrate that our approach with up to third-order and global features outperforms the state-of-the-art dual decomposition and MCMC sampling methods when evaluated on 14 languages of non-projective CoNLL datasets.
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
Persistent DSpace Link
DOI of Published Version
http://emnlp2014.org/papers.html
