Revisiting the Design Issues of Local Models for Japanese Predicate-Argument Structure Analysis
This work addresses the design of local models for Japanese predicate-argument structure analysis, showing incremental improvements over existing global models.
The study tackled the problem of limited performance gains in Japanese predicate-argument structure analysis by demonstrating that a sophisticated local model, enhanced with recent feature embedding methods and neural network-based feature combination learning, outperforms state-of-the-art global models, achieving a higher F1 score on a common benchmark dataset.
The research trend in Japanese predicate-argument structure (PAS) analysis is shifting from pointwise prediction models with local features to global models designed to search for globally optimal solutions. However, the existing global models tend to employ only relatively simple local features; therefore, the overall performance gains are rather limited. The importance of designing a local model is demonstrated in this study by showing that the performance of a sophisticated local model can be considerably improved with recent feature embedding methods and a feature combination learning based on a neural network, outperforming the state-of-the-art global models in $F_1$ on a common benchmark dataset.