Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
This addresses the challenge of expensive annotation for Japanese PAS analysis, offering a more efficient solution for natural language processing tasks in Japanese.
The paper tackles the problem of Japanese predicate-argument structure analysis, which is difficult due to zero anaphora resolution, by proposing a semi-supervised adversarial training model that uses raw corpora to overcome annotation costs, and it outperforms existing state-of-the-art models.
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.