Text corpus size is an important issue when building a language model (LM). This is a particularly important issue for languages where little data is available. This paper introduces an LM adaptation technique to improve an LM built using a small amount of task-dependent text with the help of a machine-translated text corpus. Icelandic speech recognition experiments were performed using data, m...

This paper proposes a lexicon-constrained character model that combines both word and character features to solve complicated issues in Chinese morphological analysis. A Chinese character-based model constrained by a lexicon is built to acquire word building rules. Each character in a Chinese sentence is assigned a tag by the proposed model. The word segmentation and partof-speech tagging resul...

An unsupervised method for word sense disambiguation is proposed. The sense of the word is chosen to be the most similar to the senses of other words that appear in the corpus in similar contexts. Training consists of building a weighted list of related words (quasi-synonyms) for each word; the weights are obtained by measuring similarity between the word’s contexts. We adapt the algorithm of M...

In the last decade the term “Ontology” has become a fashionable word inside the Knowledge Engineering Community. Although there are several methodologies and methods for building ontologies they are not fully mature if we compare them with software and knowledge engineering techniques. In this paper we propose a novel approach for building university curricula ontology through analysis of real ...

In class, we approached critical phenomena from the view point of correlation functions and discussed renormalization group methods for obtaining values of critical exponents. Here I discuss a parallel idea that studies critical phenomena from properties of random curves which form the domain walls of the critical system. It will be shown that such random curves obey a stochastic differential e...