Hierarchical Multitask Learning with Dependency Parsing for Japanese Semantic Role Labeling Improves Performance of Argument Identification
This work addresses a specific gap in Japanese NLP by improving SRL performance, though it is incremental as it builds on existing multitask learning approaches.
The paper tackled the problem of low accuracy in Japanese semantic role labeling (SRL) for deep cases by proposing a hierarchical multitask learning method with dependency parsing, achieving state-of-the-art results and showing that multitasking with dependency parsing is mainly effective for argument identification.
With the advent of FrameNet and PropBank, many semantic role labeling (SRL) systems have been proposed in English. Although research on Japanese predicate argument structure analysis (PASA) has been conducted, most studies focused on surface cases. There are only few previous works on Japanese SRL for deep cases, and their models' accuracies are low. Therefore, we propose a hierarchical multitask learning method with dependency parsing (DP) and show that our model achieves state-of-the-art results in Japanese SRL. Also, we conduct experiments with a joint model that performs both argument identification and argument classification simultaneously. The result suggests that multitasking with DP is mainly effective for argument identification.