Inferring Morphological Rules from Small Examples using 0/1 Linear Programming
Paper in proceeding, 2019
We show how to express the problem of finding an optimal morpheme segmentation from a set of labelled words as a 0/1 linear programming problem, and how to build on this to analyse a language’s morphology. The result is an automatic method for segmentation and labelling that works well even when there is very little training data available.
morpheme segmentation, integer linear programming
Author
Ann Lillieström
Chalmers, Computer Science and Engineering (Chalmers), Functional Programming
Koen Claessen
Chalmers, Computer Science and Engineering (Chalmers), Functional Programming
Nicholas Smallbone
Chalmers, Computer Science and Engineering (Chalmers), Functional Programming
22nd Nordic Conference on Computational Linguistics (NoDaLiDa)
1650-3686 (ISSN) 1650-3740 (eISSN)
164-174978-91-7929-995-8 (ISBN)
the 22nd Nordic Conference on Computational Linguistics (NoDaLiDa)
Turku, Finland,
Turku, Finland,
Subject Categories
Language Technology (Computational Linguistics)
Computer Science