Design, Implementation and Evaluation of an Inflectional Morphology Finite State Transducer for Irish
Machine Translation, 18 (3):
173--193 (2003)Abstract
Minority languages must endeavour to keep up with and avail of language technology advances if they are to prosper in the modern world. Finite state technology is mature, stable and robust. It is scalable and has been applied successfully in many areas of linguistic processing, notably in phonology, morphology and syntax. In this paper, the design, implementation and evaluation of a morphological analyser and generator for Irish using finite state transducers is described. In order to produce a high-quality linguistic resource for NLP applications, a complete set of inflectional morphological rules for Irish is handcrafted, as is the initial test lexicon. The lexicon is then further populated semi-automatically using both electronic and printed lexical resources. Currently we achieve coverage of 89\% on unrestricted text. Finally we discuss a number of methodological issues in the design of NLP resources for minority languages.