János Csirik

Details der Publikationsliste

Zeitraum

1998 - 2009

Anzahl

16

Co-Autoren

A manually annotated HTML corpus for a novel scientific trend analysis (2009)

Richárd Farkas, Róbert Ormándi, Márk Jelasity, János Csirik

Here we present a manually annotated corpus of web pages and annotation tool for Web Content Mining. The corpus is extensively annotated, has a hierarchical label structure and is freely available...

Manually Annotated Hungarian Corpus (2009)

Zoltán Alexin, Tibor Gyimóthy, Csaba Hatvani, László Tihanyi, János Csirik, Károly Bibok, ...

Current paper presents the results of a two-year project during which a consortium of the University of Szeged and the MorphoLogic Ltd. Budapest developed a morpho-syntactically parsed and annotated...

ON NAIVE BAYES IN SPEECH RECOGNITION (2008)

László Tóth, András Kocsor, János Csirik

The currently dominant speech recognition technology, hidden Markov modeling, has long been criticized for its simplistic assumptions about speech, and especially for the naive Bayes combination rule...

The BioScope corpus: biomedical texts annotated for uncertainty, negation and their scopes (2008)

Vincze, Veronika, Szarvas, György, Farkas, Richárd, Móra, György, Csirik, János

Abstract Background Detecting uncertain and negative assertions is essential in most BioMedical Text Mining tasks where, in general, the aim is to derive factual knowledge from textual data. This...

Preface CONFERENCE OF PHD STUDENTS IN COMPUTER SCIENCE Volume of extended abstracts (2008)

De Attila, József Nominata, Miklós Bartha, Tibor Csendes, János Csirik, ...

This conference is a kind of an experiment: the organizers have tried to get together those PhD students who work on any fields of computer science and its applications to help them possibly in...

Construction of the Hungarian EuroWordNet Ontology and its Application to Information Extraction ∗ (2008)

Zoltán Alexin, János Csirik, György Szarvas, Márton Miháltz

inf.u-szeged.hu This report describes a recent Hungarian project begun in the spring of 2005. The goals of the project are to produce a Hungarian version of the EuroWordNet ontology database, to...

The Szeged Corpus: A POS tagged and syntactically annotated Hungarian natural language corpus (2004)

Dóra Csendes, Tibor Gyimóthy, János Csirik

The Szeged Corpus is a manually annotated natural language corpus currently comprising 1.2 million word entries, 145 thousand different word forms, and an additional 225 thousand punctuation marks....

Union Slices for Program Maintenance (2002)

Arpad Beszedes Csaba, Árpád Beszédes, Csaba Faragó, Zsolt Mihály Szabó, János Csirik, Tibor Gyimóthy

static slices are specifically proposed for software maintenance and program understanding. Unfortunately, in many cases static slices are overly conservative and therefore too large to supply useful...

Fast Independent Component Analysis in Kernel Feature Spaces (2001)

András Kocsor, János Csirik

Abstract. It is common practice to apply linear or nonlinear feature extraction methods before classification. Usually linear methods are faster and simpler than nonlinear ones but an idea...

Dynamic slicing method for maintenance of large C programs (2001)

Árpád Beszédes, Tamás Gergely, Zsolt Mihály Szabó, János Csirik, Tibor Gyimóthy

Different program slicing methods are used for maintenance, reverse engineering, testing and debugging. Slicing algorithms can be classified as static slicing and dynamic slicing methods. In several...

A Comparative Study of Several Feature Transformation and Learning Methods for Phoneme Classification (2000)

András Kocsor, László Tóth, András Kuba, Kornél Kovács, Márk Jelasity, Tibor Gyimóthy, ...

. This paper examines the applicability of some learning techniques for speech recognition, more precisely, for the classi cation of phonemes represented by a particular segment model. The methods...

A Comparative Study of Several Feature Transformation and Learning Methods for Phoneme Classification,” Int (2000)

András Kocsor, László Tóth, András Kuba, Kornél Kovács, Tibor Gyimóthy, János Csirik

Abstract. This paper examines the applicability of some learning techniques for speech recognition, more precisely, for the classification of phonemes represented by a particular segment model. The...

On-line and off-line approximation algorithms for vector covering problems. Algorithmica (1998)

Noga Alon, Yossi Azar, János Csirik, Leah Epstein, Gerhard J. Woeginger

This paper deals with vector covering problems in d-dimensional space. The input to a vector covering problem consists of a set X of d-dimensional vectors in [0, 1] d. The goal is to partition X into...