Predicting Speech Errors in Mandarin Based on Word Frequency
Predicting Speech Errors in Mandarin Based on Word Frequency
Résumé
This paper investigates the effect of word frequency on the occurrence of speech errors in Mandarin. A corpus of 390 speech errors along with their surrounding linguistic context was gathered. The information of word frequency was extracted from the Academia Sinica Corpus. Our analysis with a computational classifier based on conditional inference trees shows that intended words having a frequency lower than words of the surrounding context are more likely to generate speech errors.