Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
arXiv:1806.00971
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.
arXiv commentAccepted by ACL-2018. 9 pages, 3 figures
References in corpus (5)
- Improved Techniques for Training GANs
- Unsupervised and Semi-supervised Learning with Categorical Generative Adversarial Networks
- Adversarial Learning for Neural Dialogue Generation
- Adversarial Generation of Natural Language
- Revisiting the Design Issues of Local Models for Japanese Predicate-Argument Structure Analysis