A general computational model for word-form recognition and production

Abstract

A language independent model for recognition and production of word forms is presented. This "two-level model" is based on a new way of describing morphological alternations. All rules describing the morphophonological variations are parallel and relatively independent of each other. Individual rules are implemented as finite state automata, as in an earlier model due to Martin Kay and Ron Kaplan. The two-level model has been implemented as an operational computer programs in several places. A number of operational two-level descriptions have been written or are in progress (Finnish, English, Japanese, Rumanian, French, Swedish, Old Church Slavonic, Greek, Lappish, Arabic, Icelandic). The model is bidirectional and it is capable of both analyzing and synthesizing word-forms.

Minimally supervised morphological analysis by multimodal alignment

“…The two-level model of morphology (Koskenniemi, 1983) has been extremely successful in manually capturing the morphological processes of the world's languages. The context sensitive stem-change models used in this current paper have been partially inspired by this framework.…”

Unsupervised segmentation of words using prior distributions of morph length and frequency

“…Reference morpheme sequences for the words are obtained using existing software for automatic morphological analysis based on the two-level morphology of Koskenniemi (1983). For each word form, the analyzer outputs the base form of the word together with grammatical tags.…”

Building a shallow Arabic Morphological Analyzer in one day

“…Use language rules which are programmed in a finite state transducer (FST). Koskenniemi proposed a two-level morphology system for language morphology which led to Antworth's two-level morphology system PC-KIMMO [9] [19]. Later, Beesley and Buckwalter developed an Arabic morphology system ALPNET that uses a slightly enhanced implementation of PC-KIMMO [10].…”