Modal Verbs in Learner Corpus Based on Feature Extraction Algorithm

The use of modal verbs is a very important grammatical item in English, and it is also a difficult point in Chinese learners’ learning. The study of modal meaning has always been the focus of linguists’ attention, and modal verbs, as an important means to realize modal meaning, have attracted more and more attention. Chinese learners’ use of English modal verbs can show their English proficiency to some extent. Linguists believe that it is of great significance to language communication, and argumentative paper is a genre article that analyzes and discusses a certain problem or matter, and then expresses the speaker's own views, attitudes, positions and opinions. It can best reflect personal feelings, so the expression of modality is obvious in argumentative paper. Based on the corpus, this paper investigates the semantic acquisition of modal verbs by Chinese college English learners. It is found that there is a significant difference between the frequency distribution of English modal verbs used by English learners in written language and that of English native speakers, that is, the semantic acquisition of modal verbs by college English learners is not authentic. Therefore, the purpose of this study is to investigate the choice tendency, semantic choice and usage of typical sentence patterns of modal verbs by Chinese English learners, and to analyze the empirical research methods of the usage characteristics of modal verbs. Corpus-based approach provides reliable linguistic evidence for language research, helps learners pay attention to the usage norms of native speakers and make choices of modal verbs close to those of native speakers.