TY - CHAP AU - Novák, Attila AU - Novák, Borbála ED - Berend, Gábor ED - Gosztolya, Gábor ED - Vincze, Veronika TI - Személyes adatok azonosítása és automatikus lecserélése magyar nyelvű szövegekben T2 - XX. Magyar Számítógépes Nyelvészeti Konferencia PB - Szegedi Tudományegyetem CY - online kiadás SN - 9789633069738 PY - 2024 SP - 117 EP - 129 PG - 13 UR - https://m2.mtmt.hu/api/publication/34560602 ID - 34560602 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Berkecz, Péter AU - Zombori, Tamás AU - Banga, Gergő AU - Szabó, Gergő AU - Szántó, Zsolt AU - Novák, Attila AU - Farkas, Richárd ED - Berend, Gábor ED - Gosztolya, Gábor ED - Vincze, Veronika TI - SHunQA: egy nyíltkérdés-megválaszoló rendszer T2 - XX. Magyar Számítógépes Nyelvészeti Konferencia PB - Szegedi Tudományegyetem CY - online kiadás SN - 9789633069738 PY - 2024 SP - 73 EP - 84 PG - 12 UR - https://m2.mtmt.hu/api/publication/34531850 ID - 34531850 LA - Hungarian DB - MTMT ER - TY - CHAP AU - Novák, Attila AU - Novák, Borbála AU - Zombori, Tamás AU - Szabó, Gergő AU - Szántó, Zsolt AU - Farkas, Richárd TI - A Question Answering Benchmark Database for Hungarian T2 - Proceedings of the 17th Linguistic Annotation Workshop (LAW-XVII) PB - Association for Computational Linguistics (ACL) CY - Stroudsburg (PA) SN - 9781959429838 PY - 2023 SP - 188 EP - 198 PG - 11 DO - 10.18653/v1/2023.law-1.19 UR - https://m2.mtmt.hu/api/publication/34161870 ID - 34161870 LA - English DB - MTMT ER - TY - CHAP AU - Novák, Attila AU - Novák, Borbála ED - Alberto, Simões ED - Mario, Marcelo Berón ED - Filipe, Portela TI - A Pseudonymization Prototype for Hungarian T2 - 12th Symposium on Languages, Applications and Technologies (SLATE 2023) PB - Schloss Dagstuhl Leibniz-Zentrum für Informatik CY - Wadern SN - 9783959772914 T3 - OASIcs - OpenAccess Series in Informatics, ISSN 2190-6807 ; 113. PY - 2023 SP - 3:1 EP - 3:10 DO - 10.4230/OASIcs.SLATE.2023.3 UR - https://m2.mtmt.hu/api/publication/34158531 ID - 34158531 LA - English DB - MTMT ER - TY - CHAP AU - Novák, Attila AU - Novák, Borbála ED - Gelbukh, Alexander TI - Identification of Lemmatization Errors Using Neural Models T2 - Computational Linguistics and Intelligent Text Processing PB - Springer Netherlands CY - Cham SN - 9783031237935 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 13396. PY - 2023 SP - 399 EP - 407 PG - 9 DO - 10.1007/978-3-031-23793-5_32 UR - https://m2.mtmt.hu/api/publication/34158455 ID - 34158455 LA - English DB - MTMT ER - TY - CHAP AU - Novák, Attila AU - Novák, Borbála ED - Gelbukh, Alexander TI - POS, ANA and LEM: Word Embeddings Built from Annotated Corpora Perform Better (Best Paper Award, Second Place) T2 - Computational Linguistics and Intelligent Text Processing PB - Springer Netherlands CY - Cham SN - 9783031237935 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 13396. PY - 2023 SP - 360 EP - 370 PG - 11 DO - 10.1007/978-3-031-23793-5_29 UR - https://m2.mtmt.hu/api/publication/33675492 ID - 33675492 N1 - Conference code: 291039 Export Date: 8 June 2023 Correspondence Address: Novák, A.; Pázmány Péter Catholic University Faculty of Information Technology and Bionics, Práter u. 50/a, Hungary; email: novak.attila@itk.ppke.hu Funding details: Nemzeti Kutatási Fejlesztési és Innovációs Hivatal, NKFIH Funding text 1: Acknowledgments. This research was implemented with support provided by grants FK125217 and PD125216 of the National Research, Development and Innovation Office of Hungary financed under the FK17 and PD17 funding schemes. LA - English DB - MTMT ER - TY - JOUR AU - Kahla, Mram AU - Novák, Attila AU - Yang, Zijian Győző TI - Fine-tuning and multilingual pre-training for abstractive summarization task for the Arabic language JF - ANNALES MATHEMATICAE ET INFORMATICAE J2 - ANN MATH INFORM VL - 57 PY - 2023 SP - 24 EP - 35 PG - 12 SN - 1787-5021 DO - 10.33039/ami.2022.11.002 UR - https://m2.mtmt.hu/api/publication/33624221 ID - 33624221 LA - English DB - MTMT ER - TY - CHAP AU - Novák, Attila AU - Novák, Borbála ED - Berend, Gábor ED - Gosztolya, Gábor ED - Vincze, Veronika TI - MILQA kérdés-válasz benchmark adatbázis T2 - XIX. Magyar Számítógépes Nyelvészeti Konferencia, MSZNY-2023 PB - Szegedi Tudományegyetem TTIK, Informatikai Intézet CY - Szeged SN - 9789633069127 PY - 2023 SP - 203 EP - 216 PG - 14 UR - https://m2.mtmt.hu/api/publication/33614189 ID - 33614189 LA - Hungarian DB - MTMT ER - TY - JOUR AU - Novák, Attila AU - Novák, Borbála TI - Cross-lingual transfer of knowledge in distributional language models: Experiments in Hungarian JF - ACTA LINGUISTICA ACADEMICA J2 - ACTA LING ACAD VL - 69 PY - 2022 IS - 4 SP - 405 EP - 449 PG - 45 SN - 2559-8201 DO - 10.1556/2062.2022.00580 UR - https://m2.mtmt.hu/api/publication/33287822 ID - 33287822 AB - In this paper, we argue that the very convincing performance of recent deep-neural-model-based NLP applications has demonstrated that the distributionalist approach to language description has proven to be more successful than the earlier subtle rule-based models created by the generative school. The now ubiquitous neural models can naturally handle ambiguity and achieve human-like linguistic performance with most of their training consisting only of noisy raw linguistic data without any multimodal grounding or external supervision refuting Chomsky's argument that some generic neural architecture cannot arrive at the linguistic performance exhibited by humans given the limited input available to children. In addition, we demonstrate in experiments with Hungarian as the target language that the shared internal representations in multilingually trained versions of these models make them able to transfer specific linguistic skills, including structured annotation skills, from one language to another remarkably efficiently. LA - English DB - MTMT ER - TY - CHAP AU - Novák, Attila AU - Novák, Borbála ED - Nicoletta, Calzolari ED - Frédéric, Béchet ED - Philippe, Blache ED - Khalid, Choukri ED - Chritopher, Cieri ED - Thierry, Declerk ED - Sara, Goggi ED - Hitoshi, Isahara ED - Bente, Maegaard ED - Joseph, Mariani ED - Hélene, Mazo ED - Jan, Odijk ED - Stelios, Piperidis TI - NerKor+Cars-OntoNotes++ T2 - Proceedings of the 13th Language Resources and Evaluation Conference PB - European Language Resources Association (ELRA) CY - Paris SN - 9791095546726 PY - 2022 SP - 1907 EP - 1916 PG - 10 UR - https://m2.mtmt.hu/api/publication/33118689 ID - 33118689 LA - English DB - MTMT ER -