Randomized greedy inference for joint segmentation, POS tagging and dependency parsing
Name
Barzilay_Randomized greedy.pdf
Size
587.06 KB
Format
Adobe PDF
Checksum (MD5)
6b0690476d4601ff122e08470cd07ad9
Author(s)
Zhang, Yuan
Li, Chengtao
Barzilay, Regina
Darwish, Kareem
Date Issued
January 2015
Journal
Conference Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
Publisher
Association for Computational Linguistics
Citation
Zhang, Yuan, Chengtao Li, Regina Barzilay and Kareem Darwish. "Randomized Greedy Inference for Joint Segmentation, POS Tagging and
Dependency Parsing." Conference: Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (January 2015. Denver, Colorado, May 31 - June 5, 2015) pp. 42-52.
Version
Author's final manuscript
Abstract
In this paper, we introduce a new approach for joint segmentation, POS tagging and dependency parsing. While joint modeling of these tasks addresses the issue of error propagation inherent in traditional pipeline archi-tectures, it also complicates the inference task. Past research has addressed this challenge by placing constraints on the scoring function. In contrast, we propose an approach that can handle arbitrarily complex scoring functions. Specifically, we employ a randomized greedy algorithm that jointly predicts segmentations, POS tags and dependency trees. Moreover, this architecture readily handles different seg-mentation tasks, such as morphological seg-mentation for Arabic and word segmentation for Chinese. The joint model outperforms the state-of-the-art systems on three datasets, obtaining 2.1% TedEval absolute gain against the best published results in the 2013 SPMRL shared task.
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://dblp.dagstuhl.de/db/conf/naacl/naacl2015.html
