Low-Rank Tensors for Scoring Dependency Structures
Name
Barzilay_Low-rank tensors.pdf
Size
277.02 KB
Format
Adobe PDF
Checksum (MD5)
4553483b2ee34d85d8f774a3e0d53951
Author(s)
Lei, Tao
Zhang, Yuan
Barzilay, Regina
Jaakkola, Tommi S.
Date Issued
June 2014
Journal
Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics
Publisher
Association for Computational Linguistics
Citation
Lei, Tao, Yuan Zhang, Regina Barzilay, and Tommi Jaakkola. "Low-Rank Tensors for Scoring Dependency Structures." 52nd Annual Meeting of the Association for Computational Linguistics (June 2014).
Version
Author's final manuscript
Abstract
Accurate scoring of syntactic structures such as head-modifier arcs in dependency parsing typically requires rich, high-dimensional feature representations. A small subset of such features is often selected manually. This is problematic when features lack clear linguistic meaning as in embeddings or when the information is blended across features. In this paper, we use tensors to map high-dimensional feature vectors into low dimensional representations. We explicitly maintain the parameters as a low-rank tensor to obtain low dimensional representations of words in their syntactic roles, and to leverage modularity in the tensor for easy training with online algorithms. Our parser consistently outperforms the Turbo and MST parsers across 14 different languages. We also obtain the best published UAS results on 5 languages.
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://acl2014.org/acl2014/P14-1/index.html
