Measuring language similarity using trigrams: Limitations of language identification

• Main Authors: Oco, Nathaniel, Ilao, Joel P., Roxas, Rachel Edita, Syliongka, Leif Romeritch
• Format: text
• Published: Animo Repository 2013
• Subjects: Computational linguistics; Philippine languages—Data processing; Similarity (Language learning); Computer Sciences
• Online Access: https://animorepository.dlsu.edu.ph/faculty_research/2738
• Institution: De La Salle University

Computational approaches in language identification often result in high number of false positives and low recall rates, especially if the languages involved come from the same subfamily. In this paper, we aim to determine the cause of this problem by measuring language similarity through trigrams....