Herein, we present the process of developing the first Hungarian Dependency TreeBank. First, short references are made to dependency grammars we considered important in the development of our Treebank. Second, mention is made of existing dependency corpora for other languages. Third, we present the steps of converting the Szeged Treebank into dependency-tree format: from the originally phrase-s...

Zoltan Alexin Department of Informatics University of Szeged [email protected]—szeged.hu Tibor Gyinnithy Research Group on Artifical Intelligence at University of Szeged [email protected]—szeged.hu Csaba Hatvani Department of Informatics University of Szeged [email protected]—szeged.hu LaszlO Tihanyi MorphoLogic Budapest [email protected] Janos Csirik Department of Informatics University of Szeged csiri...

We propose a novel hierarchical clustering algorithm for data-sets in which only pairwise distances between the points are provided. The classical Hungarian method is an efficient algorithm for solving the problem of minimal-weight cycle cover. We utilize the Hungarian method as the basic building block of our clustering algorithm. The disjoint cycles, produced by the Hungarian method, are view...

Abstact: The M-3 computer was constructed by members of the Cybernetics Research Group of the Hungarian Academy of Sciences (Hung: Magyar Tudományos Akadémia Kibernetikai Kutató Csoportja, abbr. MTA KKCs) from mid 1957 until the beginning 1959. I was a member of MTA KKCs until 1967. The Group was established for the sole purpose of constructing the first Hungarian electronic tube computer, firs...

JHU/APL has long espoused the use of language-neutral methods for cross-language information retrieval. This year we participated in the ad hoc cross-language track and submitted both monolingual and bilingual runs. We undertook our first investigations in the Bulgarian and Hungarian languages. In our bilingual experiments we used several nontraditional CLEF query languages such as Greek, Hunga...

In this paper we present some lessons learned from building vizsla, the keyword search and topic classification system used on the largest Hungarian portal, [origo.hu]. Based on a simple statistical language model, and the largescale supporting evidence from vizsla, we argue that in topic classification only positive ev-

A system of phonological rules and representations has at least two aims: one is to describe the way in which words (and larger stretches of utterances) are realized in speech, and to state which logically possible streams of speech sounds are legitimate in the language under description – this is part of observational adequacy. The other aim is to capture the pattern of sounds characteristic o...