An Estonian Morphological Analyser and the Impact of a Corpus on Its Development

The paper describes a morphological analyser for Estonian and how using a text corpus influenced the process of creating it and the resulting program itself. The influence is not limited with the lexicon only, but is noticeable in the resulting algorithm and implementation too. When work on the analyser started, there was no computational treatment of Estonian derivatives and compounds. After some cycles of development and testing on the corpus, we came up with an acceptable algorithm for their treatment. Both the morphological analyser and the speller based on it have been successfully marketed.