Automatic Genre Classification via N-grams of Part-of-Speech Tags

Recurring sequences of words have long been considered as a signifier of different genres and registers by corpus linguists. The previous research mainly focused on lexical n-grams. Nevertheless, n-grams of other linguistic features, such as part-of-speech, have been less studied. The current study is expected to examine whether n-grams of part-of-speech tags extracted from a large corpus can be a discriminator of different genres. The results show that a strong correlation exists between the information about n-grams of part-of-speech tags and the genre of the text.