Please use this identifier to cite or link to this item: http://scholarbank.nus.edu.sg/handle/10635/40820
Title: K-best combination of syntactic parsers
Authors: Zhang, H. 
Zhang, M.
Tan, C.L. 
Li, H.
Issue Date: 2009
Source: Zhang, H.,Zhang, M.,Tan, C.L.,Li, H. (2009). K-best combination of syntactic parsers. EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009 : 1552-1560. ScholarBank@NUS Repository.
Abstract: In this paper, we propose a linear model-based general framework to combine k-best parse outputs from multiple parsers. The proposed framework leverages on the strengths of previous system combination and re-ranking techniques in parsing by integrating them into a linear model. As a result, it is able to fully utilize both the logarithm of the probability of each k-best parse tree from each individual parser and any additional useful features. For feature weight tuning, we compare the simulated-annealing algorithm and the perceptron algorithm. Our experiments are carried out on both the Chinese and English Penn Treebank syntactic parsing task by combining two stateof-the-art parsing models, a head-driven lexicalized model and a latent-annotation-based un-lexicalized model. Experimental results show that our F-Scores of 85.45 on Chinese and 92.62 on English outperform the previously best-reported systems by 1.21 and 0.52, respectively. © 2009 ACL and AFNLP.
Source Title: EMNLP 2009 - Proceedings of the 2009 Conference on Empirical Methods in Natural Language Processing: A Meeting of SIGDAT, a Special Interest Group of ACL, Held in Conjunction with ACL-IJCNLP 2009
URI: http://scholarbank.nus.edu.sg/handle/10635/40820
Appears in Collections:Staff Publications

Show full item record
Files in This Item:
There are no files associated with this item.

Page view(s)

69
checked on Dec 9, 2017

Google ScholarTM

Check


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.