Automatic Extraction of Idioms & Proverbs and Stemming of Verbs.

      Аннотация: In the first part of the report, Identification of various idioms / proverbs and their variations has been done using the proposed statistical approach of extracting idioms and proverbs. In the second part of the report, the proposed approach used in extraction and stemming of verbs. The proposed approach is tested against three manually created text files and the result gives 89.91% average accuracy which can be improved further.

Ключевые слова: Natural Language Processing, statistical method, Stemming