TY - JOUR JF - ITRC JO - VL - 2 IS - 1 PY - 2010 Y1 - 2010/3/01 TI - Speech Acts Classification of Persian Language Texts Using Three Machine Leaming Methods TT - N2 - The objective of this paper is to design a system to classify Persian speech acts. The driving vision for this work is to provide inteUigent systems such as text to speech, machine translation, text summarization, etc. that are sensitive to the speech acts of the input texts and can pronounce the corresponding intonation correctly. Seven speech acts were considered and 3 classification methods including (1) Naive Bayes, (2) K-Nearest Neighbors (KNN), and (3) Tree learner were used. The performance of speech act classification was evaluated using these methods including 10- Fold Cross-Validation, 70-30 Random Sampling and Area under ROC. KNN with an accuracy of 72% was shown to be the best classifier for the classification of Persian speech acts. It was observed that the amount of labeled training data had an important role in the classification performance. SP - 65 EP - 71 AU - Homayounpour, Mohammad Mehdi AU - Soltani Panah, Arezou AD - Lab. for Intelligent Signal and Speech Proc. Department of Computer Engineering and IT Amirkabir University of Technology Tehran, Iran KW - Speech act KW - Persian language KW - text processing KW - Text To Speech KW - Naive Bayes KW - K-Nearest Neighbors KW - Tree learner UR - http://ijict.itrc.ac.ir/article-1-272-en.html ER -