Kaitlyn Price
2014
Morphological parsing of Swahili using crowdsourced lexical resources
Patrick Littell
|
Kaitlyn Price
|
Lori Levin
Proceedings of the Ninth International Conference on Language Resources and Evaluation (LREC'14)
We describe a morphological analyzer for the Swahili language, written in an extension of XFST/LEXC intended for the easy declaration of morphophonological patterns and importation of lexical resources. Our analyzer was supplemented extensively with data from the Kamusi Project (kamusi.org), a user-contributed multilingual dictionary. Making use of this resource allowed us to achieve wide lexical coverage quickly, but the heterogeneous nature of user-contributed content also poses some challenges when adapting it for use in an expert system.