Detection of Mistakes in Japanese Learner’s Composition by Machine Learning –Detection of Grammatical Errors in a Clause–
-
- ZHAO Yan
- Graduate School of Engineering, Mie University
-
- TAKASE Haruhiko
- Graduate School of Engineering, Mie University
-
- KITA Hidehiko
- Graduate School of Engineering, Mie University
Bibliographic Information
- Other Title
-
- 機械学習による日本語学習者の作文からの誤り検出―1文節内の文法誤りの検出―
- キカイ ガクシュウ ニ ヨル ニホンゴ ガクシュウシャ ノ サクブン カラ ノ アヤマリ ケンシュツ : 1 ブンセツ ナイ ノ ブンポウ アヤマリ ノ ケンシュツ
Search this article
Abstract
<p>We aim to develop a system to detect Japanese learner’s mistakes automatically. In this paper, we proposed a method to detect mistakes by machine learning. Especially, we focus on mistakes that are grammatical errors which can be detected from an alone clause. We discussed features for machine learning and a learning method. Consequently, we found that random forest and features constructed by result of morphological analysis bring the best result, correct judgement rate is 76% for unknown data.</p>
Journal
-
- Journal of Japan Society for Fuzzy Theory and Intelligent Informatics
-
Journal of Japan Society for Fuzzy Theory and Intelligent Informatics 32 (5), 887-890, 2020-10-15
Japan Society for Fuzzy Theory and Intelligent Informatics
- Tweet
Details 詳細情報について
-
- CRID
- 1390004951539960704
-
- NII Article ID
- 130007926394
-
- NII Book ID
- AA1181479X
-
- ISSN
- 18817203
- 13477986
-
- NDL BIB ID
- 030701042
-
- Text Lang
- en
-
- Data Source
-
- JaLC
- NDL
- Crossref
- CiNii Articles
-
- Abstract License Flag
- Disallowed