SciSurf: Index of 'Bypassed alignment graph for learning coordination in Japanese sentences'

Bypassed alignment graph for learning coordination in Japanese sentences

Okuma, Hideharu and Hara, Kazuo and Shimbo, Masashi and Matsumoto, Yuji

Past work on English coordination has focused on coordination scope disambiguation.

Coordination remains one of the challenging problems in natural language processing.

We first describe Shimbo and Hara’s method upon which our improvements are made.

We introduce two modifications to improve the performance of Shimbo and Hara’s model in Japanese coordinate structure analysis.

We applied our improved model and Shimbo and Hara’s original model to the EDR corpus (EDR, 1995).

Table 1 summarizes the experimental results.

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.