Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis
Computation and Language
2018-06-06 v2
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.
Cite
@article{arxiv.1806.00971,
title = {Neural Adversarial Training for Semi-supervised Japanese Predicate-argument Structure Analysis},
author = {Shuhei Kurita and Daisuke Kawahara and Sadao Kurohashi},
journal= {arXiv preprint arXiv:1806.00971},
year = {2018}
}
Comments
Accepted by ACL-2018. 9 pages, 3 figures