Zobrazeno 1 - 10
of 130
pro vyhledávání: '"Horak, Ales"'
Although pre-trained named entity recognition (NER) models are highly accurate on modern corpora, they underperform on historical texts due to differences in language OCR errors. In this work, we develop a new NER corpus of 3.6M sentences from late m
Externí odkaz:
http://arxiv.org/abs/2305.16718
Publikováno v:
Logically Speaking:A Festschrift for Marie Duzi, pp. 99-112, College Publications, UK, 2022, ISBN 978-1-84890-419-4
Preparing exact and comprehensive word meaning explanations is one of the key steps in the process of monolingual dictionary writing. In standard methodology, the explanations need an expert lexicographer who spends a substantial amount of time check
Externí odkaz:
http://arxiv.org/abs/2302.13625
Autor:
Ha, Hien Thi, Horák, Aleš
Publikováno v:
Signal Processing: Image Communication 102 (2022)
While storing invoice content as metadata to avoid paper document processing may be the future trend, almost all of daily issued invoices are still printed on paper or generated in digital formats such as PDFs. In this paper, we introduce the OCRMine
Externí odkaz:
http://arxiv.org/abs/2208.04011
Publikováno v:
In Expert Systems With Applications 1 October 2024 251
The move of propaganda and disinformation to the online environment is possible thanks to the fact that within the last decade, digital information channels radically increased in popularity as a news source. The main advantage of such media lies in
Externí odkaz:
http://arxiv.org/abs/2108.11669
Autor:
del Campo, Javier, Carlos-Oliveira, Maria, Čepička, Ivan, Hehenberger, Elisabeth, Horák, Aleš, Karnkowska, Anna, Kolisko, Martin, Lara, Enrique, Lukeš, Julius, Pánek, Tomáš, Piwosz, Kasia, Richter, Daniel J., Škaloud, Pavel, Sutak, Robert, Tachezy, Jan, Hampl, Vladimír
Publikováno v:
In Trends in Microbiology February 2024 32(2):128-131
Publikováno v:
In iScience 18 August 2023 26(8)
Autor:
Duží, Marie, Horák, Aleš
The success of automated reasoning techniques over large natural-language texts heavily relies on a fine-grained analysis of natural language assumptions. While there is a common agreement that the analysis should be hyperintensional, most of the aut
Externí odkaz:
http://arxiv.org/abs/1906.07562
Publikováno v:
Names, 66:4, 246-255 (2018)
This paper describes the design and development of specific software tools used during the creation of Family Names in Britain and Ireland (FaNBI) research project, started by the University of the West of England in 2010 and finished successfully in
Externí odkaz:
http://arxiv.org/abs/1904.09234
Publikováno v:
International Journal on Artifical Intelligence Tools, World Scientific Publishing, 2019, vol. 28, No 2
This paper describes a new system for semi-automatically building, extending and managing a terminological thesaurus---a multilingual terminology dictionary enriched with relationships between the terms themselves to form a thesaurus. The system allo
Externí odkaz:
http://arxiv.org/abs/1903.10921