We have been developing methods of kanji morpheme analysis for the empirical modelling of terminology. In this paper we discuss the performance of kanji morpheme extraction and kanji sequence decomposition, both based on the same bigram statistics, focusing on the e ect of type-based and token-based trainings. The experiment shows that type-based training gives consistently better performance, ...

The ParaMor algorithm for unsupervised morphology induction, which competed in the 2007 and 2008 Morpho Challenge competitions, does not assign a numeric score to its segmentation decisions. Scoring each character boundary in each word with the likelihood that it falls at a true morpheme boundary would allow ParaMor to adjust the confidence level at which the algorithm proposes segmentations. A...

This paper presents the evaluation of Morpho Challenge Competition 2 (information retrieval). The Competition 1 (linguistic gold standard) is described in a companion paper. In Morpho Challenge 2007, the objective was to design statistical machine learning algorithms that discover which morphemes (smallest individually meaningful units of language) words consist of. Ideally, these are basic voc...

This article describes the operation and the experimental evaluation of the pronunciation modeling component of the first Hungarian large vocabulary continuous speech recognition system. The proposed method is based on the implementation of context dependent rewrite rules by weighted finite state transducers (WFSTs). The proposed phonological model decreases the error rate by 8.32% relatively c...

One could assume that the negative morpheme no in (2) is not semantically negative, but this would be dissatisfying in several respects. First of all, in general we of course would prefer not to postulate an ambiguity, on fear of missing a generalization. Second, the question arises of why it is the negative morpheme which takes on the pleonastic function, if the meaning of this item is not imp...