Article Structure
Abstract
Past work on English coordination has focused on coordination scope disambiguation.
Introduction
Coordination remains one of the challenging problems in natural language processing.
Alignment-based coordinate structure analysis
We first describe Shimbo and Hara’s method upon which our improvements are made.
Improvements
We introduce two modifications to improve the performance of Shimbo and Hara’s model in Japanese coordinate structure analysis.
Experimental setup
We applied our improved model and Shimbo and Hara’s original model to the EDR corpus (EDR, 1995).
Results
Table 1 summarizes the experimental results.
Topics
perceptron
Appears in 3 sentences as: perceptron (3)
In Bypassed alignment graph for learning coordination in Japanese sentences
- Recently, Shimbo and Hara (2007) proposed to use a large number of features to model this symmetry, and optimize the feature weights with perceptron training.
Page 1, “Introduction”
- Shimbo and Hara defined this measure as a linear function of many features associated to arcs, and used perceptron training to optimize the weight coefficients for these features from corpora.
Page 2, “Alignment-based coordinate structure analysis”
- The weight of these features, which eventually determines the score of the bypass, is tuned by perceptron just like the weights of other features.
Page 3, “Improvements”
See all papers in Proc. ACL 2009 that mention perceptron.
See all papers in Proc. ACL that mention perceptron.
Back to top.