Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis

TL;DR

This paper introduces a semi-supervised adversarial training model for Japanese predicate-argument structure analysis that leverages raw corpora to improve performance, addressing the challenge of limited annotated data.

Contribution

It proposes a novel semi-supervised adversarial training approach specifically designed for Japanese PAS analysis, utilizing raw corpora to enhance accuracy.

Findings

Model outperforms existing state-of-the-art methods

Effective use of raw corpora in semi-supervised learning

Improved handling of zero anaphora resolution

Abstract

Japanese predicate-argument structure (PAS) analysis involves zero anaphora resolution, which is notoriously difficult. To improve the performance of Japanese PAS analysis, it is straightforward to increase the size of corpora annotated with PAS. However, since it is prohibitively expensive, it is promising to take advantage of a large amount of raw corpora. In this paper, we propose a novel Japanese PAS analysis model based on semi-supervised adversarial training with a raw corpus. In our experiments, our model outperforms existing state-of-the-art models for Japanese PAS analysis.