Detecting ESL/EFL Grammatical Errors Based on N-grams and Language Corpus

• Main Authors: Yu-Lin Chen, 陳玉霖
• Other Authors: 作者未提供
• Format: Others
• Language: zh-TW
• Published: 2015
• Online Access: http://ndltd.ncl.edu.tw/handle/96165664924475060940

碩士 === 銘傳大學 === 資訊傳播工程學系碩士班 === 103 === As the number of learners of English is constantly growing, automatic error detection of ESL/EFL learners’ errors is an increasingly active area of research. This paper presents a POS-based language model for detecting grammatical errors committed by ESL/EFL learners. Some famous ESL/EFL speaking/writing corpuses are introduced and tested in this study, they are CLEC、NICT JLE、BNC、Wikipedia. We use BNC corpus to build our language model, and use CLEC、NICT JLE for test. Some error types can be detected accurately, for example: missing be verb、did not put verb root behind the word “to”、addition due to double marking. The major contributions of this research are: 1. Building an English Grammar Checker. 2. Using POS-based language model to check English grammar errors. 3. Giving feedback to users and help them to learn the correct English grammar.