Hrvatska znanstvena bibliografija (CROSBI)



Pregled bibliografske jedinice broj: 723769

Zbornik radova

Autori: Beliga, Slobodan; Meštrović, Ana; Martinčić- Ipšić, Sanda
Naslov: Toward Selectivity Based Keyword Extraction for Croatian News
( Toward Selectivity-Based Keyword Extraction for Croatian News )
Izvornik: Surfacing the Deep and the Social Web (SDSW 2014) / Rupino da Cunha, Paulo ; Nguyen, Ngoc Thanh ; Boucelma, Omar ; Cautis, Bogdan ; Velegrakis, Yannis (ur.). - Italy : CEUR Proc. vol. 1310 , 2014. 1-14.
ISSN: 1613-0073
Skup: Surfacing the Deep and the Social Web
Mjesto i datum: Italija, 19.10
Ključne riječi: keyword extraction; complex network; centrality measures; selectivity; Croatian news texts
( keyword extraction; complex network; centrality measures; selectivity; Croatian news texts )
Sažetak:
Our approach proposes a novel network measure - the node selectivity for the task of keyword extraction. The node selectivity is de- ned as the average strength of the node. Firstly, we show that selectivity- based keyword extraction slightly outperforms the extraction based on the standard centrality measures: in-degree, out- degree, betweenness, and closeness. Furthermore, from the data set of Croatian news we ex- tract keyword candidates and expand extracted nodes to word-tuples ranked with the highest in/out selectivity values. The obtained sets are evaluated on manually annotated keywords: for the set of extracted key- word candidates the average F1 score is 24.63%, and the average F2 score is 21.19% ; for the exacted word-tuples candidates the average F1 score is 25.9% and the average F2 score is 24.47%. Selectivity-based ex- traction does not require linguistic knowledge while it is purely derived from statistical and structural information of the network.
Vrsta sudjelovanja: Predavanje
Vrsta prezentacije u zborniku: Cjeloviti rad (više od 1500 riječi)
Vrsta recenzije: Međunarodna recenzija
Projekt / tema: Uniri-LangNet
Izvorni jezik: eng
Kategorija: Znanstveni
Znanstvena područja:
Računarstvo,Informacijske i komunikacijske znanosti
URL Internet adrese: http://sdsw-at-iswc2014.ipn.pt/
http://ceur-ws.org/Vol-1310/
Upisao u CROSBI: Sanda Martinčić - Ipšić (smarti@inf.uniri.hr), 27. Lis. 2014. u 08:28 sati