Napredna pretraga

Pregled bibliografske jedinice broj: 924794

Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base


Tutek, Martin; Glavaš, Goran; Šnajder, Jan; Milić-Frayling, Nataša; Dalbelo Bašić, Bojana
Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base // Proceedings of the 25th ACM International Conference on Information and Knowledge Management / Mukhopadhyay, Snehasis ; Zhai, ChengXiang (ur.).
Indianapolis, Indiana, USA: ACM, 2016. str. 2077-2080 doi:10.1145/2983323.2983913 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)


Naslov
Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base

Autori
Tutek, Martin ; Glavaš, Goran ; Šnajder, Jan ; Milić-Frayling, Nataša ; Dalbelo Bašić, Bojana

Vrsta, podvrsta i kategorija rada
Radovi u zbornicima skupova, cjeloviti rad (in extenso), znanstveni

Izvornik
Proceedings of the 25th ACM International Conference on Information and Knowledge Management / Mukhopadhyay, Snehasis ; Zhai, ChengXiang - Indianapolis, Indiana, USA : ACM, 2016, 2077-2080

ISBN
978-1-4503-4073-1

Skup
International Conference on Information and Knowledge Management

Mjesto i datum
Indianapolis, Amerika, 24-28.10.2016

Vrsta sudjelovanja
Poster

Vrsta recenzije
Međunarodna recenzija

Ključne riječi
Knowledge graphs, events in news, machine learning

Sažetak
Recent research has explored the use of Knowledge Bases (KBs) to represent documents as subgraphs of a KB concept graph and define metrics to characterize semantic relatedness of documents in terms of properties of the document concept graphs. However, none of the studies so far have examined to what degree such metrics capture a user-perceived relatedness of documents. Considering the users' explanations of how pairs of documents are related, the aim is to identify concepts in a KB graph that express the same notion of document relatedness. Our algorithm generates paths through the KB graph that originate from the terms in two documents. KB concepts where these paths intersect capture the semantic relatedness of the two starting terms and therefore the two documents. We consider how such intersecting concepts relate to the concepts in the users' explanations. The higher the users' concepts appear in the ranked list of intersecting concepts, the better the method in capturing the users' notion of document relatedness. Our experiments show that our approach outperforms a simpler graph method that uses properties of the concept nodes alone.

Izvorni jezik
Engleski

Znanstvena područja
Informacijske i komunikacijske znanosti



POVEZANOST RADA


Ustanove
Fakultet elektrotehnike i računarstva, Zagreb

Profili:

Avatar Url Martin Tutek (autor)

Avatar Url Bojana Dalbelo-Bašić (autor)

Avatar Url Jan Šnajder (autor)

Avatar Url Goran Glavaš (autor)

Citiraj ovu publikaciju

Tutek, Martin; Glavaš, Goran; Šnajder, Jan; Milić-Frayling, Nataša; Dalbelo Bašić, Bojana
Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base // Proceedings of the 25th ACM International Conference on Information and Knowledge Management / Mukhopadhyay, Snehasis ; Zhai, ChengXiang (ur.).
Indianapolis, Indiana, USA: ACM, 2016. str. 2077-2080 doi:10.1145/2983323.2983913 (poster, međunarodna recenzija, cjeloviti rad (in extenso), znanstveni)
Tutek, M., Glavaš, G., Šnajder, J., Milić-Frayling, N. & Dalbelo Bašić, B. (2016) Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base. U: Mukhopadhyay, S. & Zhai, C. (ur.)Proceedings of the 25th ACM International Conference on Information and Knowledge Management doi:10.1145/2983323.2983913.
@article{article, year = {2016}, pages = {2077-2080}, DOI = {10.1145/2983323.2983913}, keywords = {Knowledge graphs, events in news, machine learning}, doi = {10.1145/2983323.2983913}, isbn = {978-1-4503-4073-1}, title = {Detecting and Ranking Conceptual Links between Texts Using a Knowledge Base}, keyword = {Knowledge graphs, events in news, machine learning}, publisher = {ACM}, publisherplace = {Indianapolis, Amerika} }

Citati