Jun Liu, Zhengxiong Li, Yuanyu Fang, Luxuan Zhuang
{"title":"A Hybrid Method for Automatic Simplification of Japanese Sentence Patterns Based on Morphological Analysis and Grammatical Rules","authors":"Jun Liu, Zhengxiong Li, Yuanyu Fang, Luxuan Zhuang","doi":"10.1109/ICET55642.2022.9944541","DOIUrl":null,"url":null,"abstract":"In Japanese grammar, there are various Japanese sentence patterns with complicated usages. Learners of Japanese as a second language (JSL) feel that it is quite difficult to learn Japanese sentence patterns. To help JSL learners with their study of Japanese sentence patterns, this work introduces Japanese example sentence simplification which is a task of replacing difficult Japanese sentence patterns with simple Japanese sentence patterns or phrases. In this task, given an example sentence as an input, a new example sentence where the difficult Japanese sentence patterns have been replaced will be generated without changing the meaning of the original example sentence. For this purpose, we proposed a hybrid method combining morphological analysis and manual grammatical rules for identifying the difficult Japanese sentence patterns and simplifying the original example sentence. The final human evaluation results demonstrated the effectiveness of our proposed method. This proposed method can be applied to development of a Japanese/Simple Japanese parallel corpus for automatic Japanese grammar simplification and a computer-assisted language learning system (CALL) for Japanese reading comprehension.","PeriodicalId":169051,"journal":{"name":"2022 IEEE 2nd International Conference on Educational Technology (ICET)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-06-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 IEEE 2nd International Conference on Educational Technology (ICET)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICET55642.2022.9944541","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
Abstract
In Japanese grammar, there are various Japanese sentence patterns with complicated usages. Learners of Japanese as a second language (JSL) feel that it is quite difficult to learn Japanese sentence patterns. To help JSL learners with their study of Japanese sentence patterns, this work introduces Japanese example sentence simplification which is a task of replacing difficult Japanese sentence patterns with simple Japanese sentence patterns or phrases. In this task, given an example sentence as an input, a new example sentence where the difficult Japanese sentence patterns have been replaced will be generated without changing the meaning of the original example sentence. For this purpose, we proposed a hybrid method combining morphological analysis and manual grammatical rules for identifying the difficult Japanese sentence patterns and simplifying the original example sentence. The final human evaluation results demonstrated the effectiveness of our proposed method. This proposed method can be applied to development of a Japanese/Simple Japanese parallel corpus for automatic Japanese grammar simplification and a computer-assisted language learning system (CALL) for Japanese reading comprehension.