GALLO, Matej, Lubomír POPELÍNSKÝ and Karel VACULÍK. To text summarization by dynamic graph mining. Online. In S. Krajči. ITAT 2018 Proceedings,. Košice: Safarik University, Faculty of Science, Kosice, Slovakia, 2018, p. 28-34. ISBN 978-1-72726-719-8.
Other formats:   BibTeX LaTeX RIS
Basic information
Original name To text summarization by dynamic graph mining
Name in Czech To text summarization by dynamic graph mining
Authors GALLO, Matej (703 Slovakia, belonging to the institution), Lubomír POPELÍNSKÝ (203 Czech Republic, guarantor, belonging to the institution) and Karel VACULÍK (203 Czech Republic, belonging to the institution).
Edition Košice, ITAT 2018 Proceedings, p. 28-34, 7 pp. 2018.
Publisher Safarik University, Faculty of Science, Kosice, Slovakia
Other information
Original language English
Type of outcome Proceedings paper
Field of Study 10200 1.2 Computer and information sciences
Country of publisher Slovakia
Confidentiality degree is not subject to a state or trade secret
Publication form electronic version available online
RIV identification code RIV/00216224:14330/18:00105832
Organization unit Faculty of Informatics
ISBN 978-1-72726-719-8
ISSN 1613-0073
Keywords (in Czech) sumarizace textu; dolování z dynamických grafů
Keywords in English text summarization; dynamic graph mining
Changed by Changed by: RNDr. Pavel Šmerk, Ph.D., učo 3880. Changed: 30/4/2019 07:38.
Abstract
We show that frequent patterns can contribute to the quality of text summarization. Here we focus on single-document extractive summarization in English. Performance of the frequent patterns based model obtained with DGRMiner yields the most relevant sentences of all compared methods. Two out of three proposed methods outperform other methods if compared on ROUGE data.
Abstract (in Czech)
We show that frequent patterns can contribute to the quality of text summarization. Here we focus on single-document extractive summarization in English. Performance of the frequent patterns based model obtained with DGRMiner yields the most relevant sentences of all compared methods. Two out of three proposed methods outperform other methods if compared on ROUGE data.
Links
MUNI/A/0854/2017, interní kód MUName: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace VII.
Investor: Masaryk University, Category A
PrintDisplayed: 23/7/2024 02:37