TY - CHAP AU - Dodé, Réka AU - Yang, Zijian Győző ED - Berend, Gábor ED - Gosztolya, Gábor ED - Vincze, Veronika TI - Kulcsszógenerálás magyar nyelvű, hosszú szövegekből nagy nyelvi modellekkel T2 - XX. Magyar Számítógépes Nyelvészeti Konferencia PB - Szegedi Tudományegyetem CY - online kiadás SN - 9789633069738 PY - 2024 SP - 257 EP - 267 PG - 11 UR - https://m2.mtmt.hu/api/publication/34560996 ID - 34560996 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Felletár, Fanni AU - Yang, Zijian Győző AU - Babarczy, Anna ED - Berend, Gábor ED - Gosztolya, Gábor ED - Vincze, Veronika TI - Az egészség jele a szöveg EGÉSZsége? - Szövegkoherencia borderline személyiségzavarban T2 - XX. Magyar Számítógépes Nyelvészeti Konferencia PB - Szegedi Tudományegyetem CY - online kiadás SN - 9789633069738 PY - 2024 SP - 201 EP - 214 PG - 14 UR - https://m2.mtmt.hu/api/publication/34560795 ID - 34560795 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Yang, Zijian Győző AU - Dodé, Réka AU - Héja, Enikő AU - Laki, László János AU - Ligeti-Nagy, Noémi AU - Madarász, Gábor AU - Váradi, Tamás ED - Berend, Gábor ED - Gosztolya, Gábor ED - Vincze, Veronika TI - ParancsPULI: Az utasításkövető PULI-modell T2 - XX. Magyar Számítógépes Nyelvészeti Konferencia PB - Szegedi Tudományegyetem CY - online kiadás SN - 9789633069738 PY - 2024 SP - 61 EP - 72 PG - 12 UR - https://m2.mtmt.hu/api/publication/34557892 ID - 34557892 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Kovásznai, Gergely AU - Kiss, D.H. AU - Mlinkó, P. TI - Formal verification for quantized neural networks JF - ANNALES MATHEMATICAE ET INFORMATICAE J2 - ANN MATH INFORM VL - 57 PY - 2023 SP - 36 EP - 48 PG - 13 SN - 1787-5021 DO - 10.33039/ami.2023.04.003 UR - https://m2.mtmt.hu/api/publication/34623343 ID - 34623343 N1 - Department of Computational Science, Eszterházy Károly Catholic University, Hungary Pázmány Péter Catholic University, Hungary Export Date: 18 February 2024 AB - Despite of deep neural networks are being successfully used in many fields of computing, it is still challenging to verify their trustiness. Previously it has been shown that binarized neural networks can be verified by being encoded into Boolean constraints. In this paper, we generalize this encoding to quantized neural networks (QNNs). We demonstrate how to implement QNNs in Python, using the Tensorflow and Keras libraries. Also, we demonstrate how to implement a Boolean encoding of QNNs, as part of our tool that is able to run a variety of solvers to verify QNNs. © 2023, Eszterhazy Karoly College. All rights reserved. LA - English DB - MTMT ER - TY - JOUR AU - Osváth, Mátyás AU - Yang, Zijian Győző AU - Kósa, Karolina TI - Analyzing Narratives of Patient Experiences: A BERT Topic Modeling Approach JF - ACTA POLYTECHNICA HUNGARICA J2 - ACTA POLYTECH HUNG VL - 20 PY - 2023 IS - 7 SP - 153 EP - 171 PG - 19 SN - 1785-8860 DO - 10.12700/APH.20.7.2023.7.9 UR - https://m2.mtmt.hu/api/publication/34560870 ID - 34560870 AB - Due to healthcare systems increased focus on healthcare quality and patientcentered care, the patients’ perspective of delivered healthcare, has become an important part of healthcare service evaluations. Patient experiences can be used to improve the quality of care, as they reveal important information about health care encounters. An increasing number of organizations systematically collect and analyze patient experience data. The aim of our study was to identify major topics in narratives of patients’ healthcare related experiences and analyze the reactions of readers of patient experiences. 1663 blogs and 298806 textual comments were extracted on non-solicited patient experiences from a Hungarian online forum during a 10-year period. Topic modeling with state-of-the-art BERT embeddings were used to analyze the data and extract meaningful patterns and concepts. Sentiment analysis was utilized to categorize the emotional valence of the narrative writings. The huBERT and HIL-SBERT models identified 326 and 200 topics in terms of patient experiences and 508 and 728 topics regarding the reactions to these experiences without human supervision. Conceptually similar topics were integrated into major categories with manual analysis. 94.4% of the experiences and 77.5% of comments were classified as negative, reflecting the same annual tendency over the decade. Our study uses a data-driven approach for extracting patterns of healthcare related patient opinions, in Hungary. Topic modeling, based on BERT embeddings, could provide useful information on patient perceptions and perspectives, that could improve healthcare quality and safety LA - English DB - MTMT ER - TY - JOUR AU - Hatvani, Péter AU - Laki, László János AU - Yang, Zijian Győző TI - A pseudonymization tool for Hungarian JF - ANNALES MATHEMATICAE ET INFORMATICAE J2 - ANN MATH INFORM VL - 58 PY - 2023 SP - 69 EP - 80 PG - 12 SN - 1787-5021 DO - 10.33039/ami.2023.08.009 UR - https://m2.mtmt.hu/api/publication/34560462 ID - 34560462 LA - English DB - MTMT ER - TY - GEN AU - Geda, Gábor TI - Alternatív „robotolás” lehetőségei a közoktatásban. előadás TS - előadás PY - 2023 UR - https://m2.mtmt.hu/api/publication/34495006 ID - 34495006 LA - Hungarian DB - MTMT ER - TY - GEN AU - Varga, Éva AU - Geda, Gábor TI - Interdiszciplinaritás lehetőségei a nyelvoktatás és az algoritmikus gondolkodás területén. előadás TS - előadás PY - 2023 UR - https://m2.mtmt.hu/api/publication/34495003 ID - 34495003 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Nagy, Benedek TI - Weighted distances and distance transforms on the triangular tiling JF - TRANSACTIONS IN GIS J2 - TRANS IN GIS VL - 27 PY - 2023 IS - 7 SP - 2042 EP - 2098 PG - 57 SN - 1361-1682 DO - 10.1111/tgis.13112 UR - https://m2.mtmt.hu/api/publication/34406590 ID - 34406590 N1 - Department of Mathematics, Faculty of Arts and Sciences, Eastern Mediterranean University, Famagusta, Turkey Department of Computer Science, Institute of Mathematics and Informatics, Eszterházy Károly Catholic University, Eger, Hungary Export Date: 18 February 2024 CODEN: TRGIF Correspondence Address: Nagy, B.; Department of Mathematics, North Cyprus, Via Mersin-10, Turkey; email: nbenedek.inf@gmail.com Funding text 1: A part of this article was presented at IWCIA 2014: 16th International Workshop on Combinatorial Image Analysis, Brno, Czech Republic (Nagy, 2014). This article can be seen as an extension of that proceedings article. Comments of the anonymous reviewers are gratefully acknowledged. AB - Digital geometry is a field in the intersection of discrete mathematics and geometry having various applications including geographical information systems (GIS). In digital spaces, in grids, distances can be defined based on steps in paths in somewhat similarly as in graph theory. However, the grids have more definite structures, thus one may obtain more concrete results, for example, close formulae, than on arbitrary graphs. In this article, the weighted (also called chamfer) distances, and based on them, the distance transform are investigated on the regular triangular grid. Three types of neighborhood relations are used on the grid, and therefore, three weights are used to define a distance function. Natural conditions are used on the weights such as they are positive and a larger step (in the usual and also in the Euclidean sense) cannot have a smaller weight than a smaller one. Some properties of the weighted distances are discussed; for example, they are proven to be metrics. We also give algorithms and formulae that compute the weighted distance of any point pair on a triangular grid. Algorithm for weighted distance transform is provided based on wave-front propagation. Therefore, these new distance functions are ready for further applications in GIS, in image processing tasks, in computer vision, in graphics, in networking, and also in other applied fields. © 2023 The Authors. Transactions in GIS published by John Wiley & Sons Ltd. LA - English DB - MTMT ER - TY - CHAP AU - Glu, Ö.E. AU - Nagy, Benedek ED - Gazdag, Z. ED - Ivan, S. ED - Kovasznai, G. TI - On Languages Generated by Signed Grammars T2 - Electronic Proceedings in Theoretical Computer Science, EPTCS VL - 388 PB - Open Publishing Association T3 - Electronic Proceedings in Theoretical Computer Science, EPTCS, ISSN 2075-2180 ; 386. PY - 2023 SP - 28 EP - 37 PG - 10 DO - 10.4204/EPTCS.388.5 UR - https://m2.mtmt.hu/api/publication/34406589 ID - 34406589 N1 - Department of Computer Science, University of California, Santa Barbara, CA 93106, United States Department of Mathematics, Eastern Mediterranean University, Famagusta, North Cyprus-10, Mersin, 99628, Turkey Department of Computer Science, Institute of Mathematics and Informatics, Eszterházy Károly Catholic University, Eger, Hungary Conference code: 192550 Export Date: 18 February 2024 AB - We consider languages defined by signed grammars which are similar to context-free grammars except productions with signs associated to them are allowed. As a consequence, the words generated also have signs. We use the structure of the formal series of yields of all derivation trees over such a grammar as a method of specifying a formal language and study properties of the resulting family of languages. © Ömer Egecio glu & Benedek Nagy. LA - English DB - MTMT ER -