Knowledge- and Labor-light Morphological Analysis1

We describe a knowledge and labor-light system for morphological analysis of fusional languages, exemplified by analysis of Czech. Our approach takes the middle road between completely unsupervised systems on the one hand and systems with extensive manually-created resources on the other. For the majority of languages and applications neither of these extreme approaches seems warranted. The knowledge-free approach lacks precision and the knowledge-intensive approach is usually too costly. We show that a system using a little knowledge can be effective. This is done by creating an open, flexible, fast, portable system for morphological analysis. Time needed for adjusting the system to a new language constitutes a fraction of the time needed for systems with extensive manually created resources: days instead of years. We tested this for Russian, Portuguese and Catalan. 1This paper differs only slightly from a paper presented at the Department of Linguistics of The Ohio State University in 2004 and finished in 2005. The morphological analyzer described in this paper was developed as part of a joint project with Anna Feldman and Chris Brew aimed at developing a portable resource-light tagger. I thank Chris Brew, Anna Feldman, Jan Hajič, Brian Joseph and Detmar Meurers for providing valuable feedback and to Steve Evans for helping me in my struggle with the English language. The work described in this paper was partially supported by NSF CAREER Award 0347799. Jirka Hana. Knowledgeand labor-light morphological analysis. OSUWPL, Volume 58, Fall 2008, pp. 52– 84. KNOWLEDGEAND LABOR-LIGHT MORPHOLOGICAL ANALYSIS 53