Morphology in the Eurotra Base Level Concept

MORPHOLOGY in the EUROTRA BASE LEVEL CONCEPT by Peter Lau and Sergei Perschke Commission of the EC, Bat. JMO L - 2920 Luxembourg ABSTRACT Xn recent years the nature and the role of a morphological component in NLP systems has attracted a lot of attention. The two-level model of Koskenniemi which relates graphemlc to morphological structure has been succesfully implemented in the form of finite state automata. Xn EUROTRA a solution which combines morphological and surface syntactic processing in one CFG implemented in a unification grammar framework has been tried out. This article contrasts these two approaches considering especially the feasibility of building morphologlcal modules for a big multilingual MT system in a decentralised R & V project. O. INTRODUCTION The development of sophisticated NLP applications has created a need for specific processing in order to be able to cope with large vocabularies without creating monstruous dictionaries. Earlier approaches often avoided morphology more or less by listing full wordforms in the dictionary or by simply segmenting some inflectional endings with a few general rules. Much recent work is based on the Two-level Model (Koskenniemi, 1983) and relates directly or indirectly to the original implementation of this model in the form of finite state transducers (FST). The original notation and implementation have been further developed and refined (cf. e.g. Black, 1986 and Bear, 1986) in order to improve compilation and runtime, debugging and rule-writing facilities. Still some problems persist and others have not been touched yet. This paper presents an alternative, but not contradictory, solution which has to some extent been tried out in the EUROTRA Machine Translation Project and argues that the two-level approach may not be entirely viable in a decentralised R&D project which aims at ~he creation of a big multilingual HT system. I. THE TWO-LEVEL MODEL The original presentation of the model (Koskenniemi, 1983) shows that it is possible to treat the inflectional morphology (including spelling rules) of a highly inflected language like Finnish by establishing correspondences between a surface alphabet and a lexical alphabet (the two levels) and using a lexicon to determine which combinations of characters and morphemes are legal. Moreover, this is done by means of declarative rules, thereby avoiding the procedural problems of generative phonology, and the algorithm used is language independent. Together with the fact that the model may bc used for synthesis as well as for analysis this is a strong argument in favour of employing a two-level approach to morphology. Later work points to some important shortcomings of the original implementation of the model in the loom of FST's (Black, 1986). Especially compilation and runtime requirements and debugging are seen to pose severe problems. In Black's words:"Debugging automata is reminiscent of debugging assembly language progranuuing in hex". Considering that the (linguistic) user is interested in the rules rather than in the low-level implementation of them, Black et al. have proceeded to develop high-level notations in the form of rules which are interpreted directly, instead of being compiled into FST's. Nonetheless, …

Content truncated to 500 words