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.

本研究提出了新的日语 PAS 分析模型，通过扩展标准的双向循环神经网络模型的输入和最后一层，结合多个 PAS 中的论元标签预测信息，使用池化和注意机制直接捕捉多个 PAS 之间的潜在相互作用，并成功地改善了间接依赖关系的情况下的预测准确性，并在标准的基准语料库上取得了新的最佳效果。