Gábor Recski
Gábor has been working on natural language technologies since 2008, when as a linguistics major at SEAS and TLP he learned to code from HP and Dániel and started working at MOKK. After a year of developing on the sequential tagger HunTag, he joined András's group at the (then still independent) SZTAKI, where he spent 4 years working on various NLP projects, including a hybrid NP-chunker, a tool for entity linking, a learner of weighted grammars, and a system for natural language understanding based on the 4lang theory of semantics. After spending 15 months at Cliqz, Gábor continued work on the 4lang library, the main topic of his dissertation, as a junior researcher at the (then still independent) Research Institute for Linguistics of the Hungarian Academy of Sciences. After finishing his dissertation in 2016, Gábor joined the faculty of BME AUT, where he continued working on graph-based models of semantics and taught an introductory course in NLP.
Since 2020 Gábor leads the TUW NLP group. In 2024 he and Ádám Kovács co-founded the TU Wien spin-off KR Labs, where they develop open-source libraries for transparent and trustworthy NLP solutions.
Contact:
+4367762968104
recski at krlabs dot eu
Full list of publications
Recent publications
2022
Á. Kovács,
K. Gémes,
A. Kornai,
G. Recski:
Explainable lexical entailment with semantic graphs.
In Natural Language Engineering.
K. Gémes,
Á. Kovács,
G. Recski:
Offensive Text Detection Across Languages and Datasets Using Rule-based and Hybrid Methods.
In CIKM’22: Advances in Interpretable Machine Learning and Artificial Intelligence Workshop.
Á. Kovács,
K. Gémes,
E. Iklódi,
G. Recski:
POTATO: exPlainable infOrmation exTrAcTion framewOrk.
In CIKM '22: Proceedings of the 31st ACM International Conference on Information & Knowledge Management.
2021
J. Bogensperger,
S. Schlarb,
A. Hanbury,
G. Recski:
DreamDrug - A crowdsourced NER dataset for detecting drugs in darknet markets.
In Proceedings of the Seventh Workshop on Noisy User-generated Text (W-NUT 2021).
G. Recski,
B. Lellmann,
Á. Kovács,
A. Hanbury:
Explainable Rule Extraction via Semantic Graphs.
In Proceedings of the Fifth Workshop on Automated Semantic Analysis of Information in Legal Text (ASAIL 2021).
K. Gémes,
Á. Kovács,
M. Reichel,
G. Recski:
Offensive text detection on English Twitter with deep learning models and rule-based systems.
In FIRE 2021: Forum for Information Retrieval Evaluation.
K. Gémes,
G. Recski:
TUW-Inf at GermEval2021: Rule-based and Hybrid Methods for Detecting Toxic, Engaging, and Fact-Claiming Comments.
In Proceedings of the GermEval 2021 Workshop on the Identification of Toxic, Engaging, and Fact-Claiming Comments.
R. Csáky,
G. Recski:
The Gutenberg Dialogue Dataset.
In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: Volume 1, Long Papers.
2020
G. Recski,
Á. Kovács,
K. Gémes,
J. Ács,
A. Kornai:
BME-TUW at SR'20: Lexical grammar induction for surface realization.
In Proceedings of the 3rd Workshop on Multilingual Surface Realisation (MSR 2020).
Á. Kovács,
K. Gémes,
G. Recski,
A. Kornai:
BMEAUT at SemEval-2020 Task 2: Lexical entailment with semantic graphs.
In Proceedings of the 14th International Workshop on Semantic Evaluation.
Á. Kovács,
J. Ács,
A. Kornai,
G. Recski:
Better Together: Modern methods plus traditional thinking in NP alignment.
In In Proceedings of 12th Edition of its Language Resources and Evaluation Conference..
2019
Á. Kovács,
E. Ács,
J. Ács,
A. Kornai,
G. Recski:
BME-UW at SR'19: Surface realization with Interpreted Regular Tree Grammars.
In Proceedings of the 2nd Workshop on Multilingual Surface Rea lisation (MSR), 2019 Conference on Empirical Methods in Natural Language Processing (EMNLP).
J. Ács,
D. Nemeskey,
G. Recski:
Building word embeddings from dictionary definitions.
In K + K = 120 Papers dedicated to László Kálmán and András Kornaion the occasion of their 60th birthdays.
E. Ács,
G. Recski:
Generating IRTG grammars from parallel data.
In Proceedings of the Automation and Applied Computer Science Workshop 2019 : AACS'19.
R. Csáky,
P. Purgai,
G. Recski:
Improving Neural Conversational Models with Entropy-Based Data Filtering.
In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL).
Á. Kovács,
G. Recski,
K. Gémes:
Machine comprehension using semantic graphs.
In Proceedings of the Automation and Applied Computer Science Workshop 2019 : AACS'19.
E. Ács,
Á. Holló-Szabó,
G. Recski:
Parsing noun phrases with Interpreted Regular Tree Grammars.
In XV. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2019).
M. Castro-Bleda,
E. Iklódi,
G. Recski,
G. Borbély:
Towards a Universal Semantic Dictionary.
In Applied Sciences 9(19).
2018
G. Recski:
Building concept definitions from explanatory dictionaries.
In International Journal of Lexicography 31/3.
E. Ács,
G. Recski:
Evaluation of Universal Dependency parsers for Hungarian.
In XIV. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2018).
J. Ács,
G. Borbély,
M. Makrai,
D. Nemeskey,
G. Recski,
A. Kornai:
Hibrid nyelvtechnológiák.
In Magyar Tudomány 2018/6.
Á. Kovács,
G. Recski:
Knowledge base population using natural language inference.
In Proceedings of Automation and Applied Computer Science Workshop.
E. Ács,
G. Recski:
Semantic parsing with Interpreted Regular Tree Grammars.
In Proceedings of the Automation and Applied Computer Science Workshop 2018 : AACS'18.
B. Kemény,
G. Recski:
Természetes nyelvi interfész menetrend- és utazástervező szolgáltatásokhoz.
In XIV. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2018).
2017
J. Ács,
D. Nemeskey,
G. Recski:
Building word embeddings from dictionary definitions.
In Papers dedicated to László Kálmán and András Kornai on the occasion of their 60th birthdays.
R. Csáky,
G. Recski:
Deep Learning Based Chatbot Models.
In National Scientific Students' Associations Conference.
B. Gyuris,
K. Mády,
G. Recski:
K + K = 120. Papers dedicated to László Kálmán and András Kornai on the occasion of their 60th birthdays.
2016
G. Recski:
Building concept graphs from monolingual dictionary entries.
In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).
G. Recski,
A. Bolevácz,
G. Borbély:
Building definition graphs using monolingual dictionaries of Hungarian.
In XII. Magyar Számítógépes Nyelvészeti Konferencia (MSZNY 2016).
G. Recski:
Computational methods in semantics.
A. Kornai,
D. Nemeskey,
G. Recski:
Detecting Optional Arguments of Verbs.
In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016).
G. Recski,
E. Iklódi,
K. Pajkossy,
A. Kornai:
Measuring semantic similarity of words using concept networks.
In Proceedings of the 1st Workshop on Representation Learning for NLP.
2015
A. Kornai,
J. Ács,
M. Makrai,
D. Nemeskey,
K. Pajkossy,
G. Recski:
Competence in lexical semantics.
In Proceedings of the Fourth Joint Conference on Lexical and Computational Semantics.
G. Recski,
J. Ács:
MathLingBudapest: Concept Networks for Semantic Similarity.
In Proceedings of the 9th International Workshop on Semantic Evaluation (SemEval 2015).
2014
2013
G. Recski:
Egy általános célú morfológiai annotáció kiterjesztése [Extending a general-purpose morphological annotation system].
In VII. Alkalmazott Nyelvészeti Doktoranduszkonferencia.
G. Recski,
A. Rung:
Identifying Epenthetic Nouns using Maximum Entropy Classification.
In VLLXX: Papers Presented to László Varga on his 70th Birthday.
D. Nemeskey,
G. Recski,
M. Makrai,
A. Zséder,
A. Kornai:
Spreading activation in language understanding.
In Proc. CSIT 2013.
A. Kornai,
A. Zséder,
G. Recski:
Structure Learning in Weighted Languages.
In Proceedings of the 13th Meeting on the Mathematics of Language (MoL 13).
2012
G. Recski,
D. Varga:
Magyar főnévi csoportok azonosítása.
In Általános {N}yelvészeti {T}anulmányok.
D. Nemeskey,
G. Recski,
A. Zséder:
Miből lesz a robot MÁV-pénztáros?.
In IX. Magyar Számitógépes Nyelvészeti Konferencia [Ninth Conference on Hungarian Computational Linguistics].
A. Zséder,
G. Recski,
D. Varga,
A. Kornai:
Rapid creation of large-scale corpora and frequency dictionaries.
In Proceedings to LREC 2012.
2011
2010
D. Nemeskey,
G. Recski,
A. Zséder,
A. Kornai:
BUDAPESTACAD at TAC.
In Proceedings of TAC 2010.
G. Recski:
Főnévi csoportok azonosítása szabályalapú és hibrid módszerekkel.
In VII. Magyar Számítógépes Nyelvészeti Konferencia.
G. Recski,
A. Kornai,
A. Zséder,
A. Kornai:
NP Alignment in Bilingual Corpora.
In Proceedings of the Seventh International Conference on Language Resources and Evaluation (LREC'10).
G. Recski:
NP Chunking in Hungarian.
2009
G. Recski,
D. Varga:
A Hungarian NP Chunker.
In The Odd Yearbook. ELTE SEAS Undergraduate Papers in Linguistics.
G. Recski,
D. Varga,
A. Zséder,
A. Kornai:
Főnévi csoportok azonosítása magyar-angol párhuzamos korpuszban.
In VI. Magyar Számitógépes Nyelvészeti Konferencia [6th Hungarian Conference on Computational Linguistics].