Extracting inflectional class assignment in Pite Saami: Nouns, verbs and those pesky adjectives

The main goal of this paper is to describe to what extent the three main open word classes in Pite Saami (nouns, verbs and adjectives) can be automatically assigned to inflectional classes in language technology, specifically for a Finite State Transducer. For each of these word classes, the relevant structural features necessary for determining inflectional class membership are described. In this, a clear difference between the behavior of nouns and verbs, on the one hand, and that of adjectives, on the other hand, is ascertained. While morphophonology, as seen in the paradigmatic behavior of all three word classes, is complex and features a number of types of stem alternations, nouns and verbs are predictable, while adjectives are not. With this in mind, a basic algorithm for extracting inflectional class assignment for nouns and verbs is presented for use in a LEXC framework. In contrast to this, adjectives must be assigned to inflectional classes manually. The main TWOLC rules used to trigger morphophonological alternations are also outlined. The Pite Saami lexicographic database that forms the backbone for the LEXC stem files is managed using FileMaker Pro database software, and the workflow used to extract and update LEXC files from that database is described, focussing on the differences between nouns and verbs, and adjectives. In this, light is shed on how, on the one hand, nominal and verbal inflectional patters are highly complex yet reliably systematic, while adjective morphophonology is complex and unpredictable.