Evaluating an ensemble model of linguistic categorization on three variable morphological patterns in Hungarian

Rácz, Péter and Rebrus, Péter and Tóth, Szilárd (2024) Evaluating an ensemble model of linguistic categorization on three variable morphological patterns in Hungarian. PROCEEDINGS OF THE ANNUAL CONFERENCE OF THE COGNITIVE SCIENCE SOCIETY, 46. pp. 4706-4711. ISSN 1069-7977

Preview

Text eScholarshipUCitem914866s3.pdf - Published Version Available under License Creative Commons Attribution. Download (299kB) | Preview

Abstract

We implemented two instance-based learners, the K-Nearest Neighbors model and the Generalized Context Model, and a rule-based learner, the Minimal Generalization Learner, adapted for linguistic data. We fit these on three distinct, variable patterns of word variation in Hungarian: paradigmatic leveling and vowel deletion in verbs and vowel harmony in nouns. We tested their predictions using a Wug task. The best learners were combined into an ensemble model for each pattern. All three learners explain variation in the test data. The best ensemble models of inflectional variation in the data combine instance-based and rule-based learners. This result suggests that the best psychologically plausible learning model of morphological variation combines instance-based and rule-based approaches and might vary from case to case.

Actions (login required)

Edit Item