We found a match
Your institution may have access to this item. Find your institution then sign in to continue.
- Title
LATTICE BASED MORPHOLOGICAL RULE INDUCTION.
- Authors
SZABÓ, G.; KOVÁCS, L.
- Abstract
In this paper we will present a novel inection learning method using lattice based algorithms. The inection grammar system is represented with a lattice of elementary inection rules, enabling the description of prefix, infix and suffix transformations as well. The proposed grammar system is ideal for highly agglutinative languages like Hungarian. We created a learning algorithm to generate the rules in an automated way from training word pair sets. Our evaluation shows that this novel method can learn both suffix and infix transformations unlike our baseline algorithm called TASR, and has a better correctness ratio than finite state transducers, too.
- Subjects
ALGORITHMS; LATTICE constants; HUNGARIAN language; SUFFIXES &; prefixes (Grammar); TRANSDUCERS
- Publication
Acta Universitatis Apulensis: Mathematics-Informatics, 2019, Issue 60, p93
- ISSN
1582-5329
- Publication type
Article
- DOI
10.17114/j.aua.2018.53.07