Automatic Estimation of Definite Articles for Proper Nouns in English

Abstract

Japanese learners of English often make article errors. Recently, many methods for detecting or correcting article errors have been proposed. In particular, such methods using machine learning achieve high accuracy. On the other hand, there is a problem that the accuracy of estimating definite articles is comparatively low. In this paper, we propose a method that estimate definite articles automatically for proper nouns. Our method use machine learning with proper nouns' own kind of features.