Seminar in Computational Linguistics
- Date: –15:00
- Location: Engelska parken 9-3042
- Lecturer: Marc Tang
- Contact person: Miryam de Lhoneux
Predicting speech errors in Mandarin based on word frequency
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.