Multi-task Learning for Japanese Predicate Argument Structure Analysis
This work addresses a specific bottleneck in Japanese natural language processing by integrating predicate and event-noun analysis, though it is incremental as it builds on existing multi-task learning approaches.
The paper tackled the problem of analyzing argument structures for both predicates and event-nouns in Japanese, which were previously handled separately or ignored, by proposing a multi-task learning method that improved performance for both tasks and achieved state-of-the-art F1 scores in predicate analysis.
An event-noun is a noun that has an argument structure similar to a predicate. Recent works, including those considered state-of-the-art, ignore event-nouns or build a single model for solving both Japanese predicate argument structure analysis (PASA) and event-noun argument structure analysis (ENASA). However, because there are interactions between predicates and event-nouns, it is not sufficient to target only predicates. To address this problem, we present a multi-task learning method for PASA and ENASA. Our multi-task models improved the performance of both tasks compared to a single-task model by sharing knowledge from each task. Moreover, in PASA, our models achieved state-of-the-art results in overall F1 scores on the NAIST Text Corpus. In addition, this is the first work to employ neural networks in ENASA.