Distance-Free Modeling of Multi-Predicate Interactions in End-to-End Japanese Predicate-Argument Structure Analysis
This addresses a crucial issue in Japanese predicate-argument structure analysis, specifically improving accuracy for indirect dependency relations, but it is incremental as it extends existing bi-RNN models.
The paper tackled the problem of capturing interactions among multiple predicate-argument structures in Japanese by proposing models that integrate label prediction information using pooling and attention mechanisms, achieving a new state of the art in overall F1 on a standard benchmark corpus.
Capturing interactions among multiple predicate-argument structures (PASs) is a crucial issue in the task of analyzing PAS in Japanese. In this paper, we propose new Japanese PAS analysis models that integrate the label prediction information of arguments in multiple PASs by extending the input and last layers of a standard deep bidirectional recurrent neural network (bi-RNN) model. In these models, using the mechanisms of pooling and attention, we aim to directly capture the potential interactions among multiple PASs, without being disturbed by the word order and distance. Our experiments show that the proposed models improve the prediction accuracy specifically for cases where the predicate and argument are in an indirect dependency relation and achieve a new state of the art in the overall $F_1$ on a standard benchmark corpus.