hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1001912

Contextualized Question Answering

Luka Bradeško ; Jožef Stefan Institute, Ljubljana, Slovenia
Lorand Dali ; Jožef Stefan Institute, Ljubljana, Slovenia
Blaž Fortuna ; Jožef Stefan Institute, Ljubljana, Slovenia
Marko Grobelnik ; Jožef Stefan Institute, Ljubljana, Slovenia
Dunja Mladenić ; Jožef Stefan Institute, Ljubljana, Slovenia
Inna Novalija ; Jožef Stefan Institute, Ljubljana, Slovenia
Boštjan Pajntar ; Jožef Stefan Institute, Ljubljana, Slovenia

Puni tekst: engleski, pdf (285 KB) str. 325-332 preuzimanja: 1.288* citiraj
APA 6th Edition
Bradeško, L., Dali, L., Fortuna, B., Grobelnik, M., Mladenić, D., Novalija, I. i Pajntar, B. (2010). Contextualized Question Answering. Journal of computing and information technology, 18 (4), 325-332. https://doi.org/10.2498/cit.1001912
MLA 8th Edition
Bradeško, Luka, et al. "Contextualized Question Answering." Journal of computing and information technology, vol. 18, br. 4, 2010, str. 325-332. https://doi.org/10.2498/cit.1001912. Citirano 22.07.2019.
Chicago 17th Edition
Bradeško, Luka, Lorand Dali, Blaž Fortuna, Marko Grobelnik, Dunja Mladenić, Inna Novalija i Boštjan Pajntar. "Contextualized Question Answering." Journal of computing and information technology 18, br. 4 (2010): 325-332. https://doi.org/10.2498/cit.1001912
Harvard
Bradeško, L., et al. (2010). 'Contextualized Question Answering', Journal of computing and information technology, 18(4), str. 325-332. https://doi.org/10.2498/cit.1001912
Vancouver
Bradeško L, Dali L, Fortuna B, Grobelnik M, Mladenić D, Novalija I i sur. Contextualized Question Answering. Journal of computing and information technology [Internet]. 2010 [pristupljeno 22.07.2019.];18(4):325-332. https://doi.org/10.2498/cit.1001912
IEEE
L. Bradeško, et al., "Contextualized Question Answering", Journal of computing and information technology, vol.18, br. 4, str. 325-332, 2010. [Online]. https://doi.org/10.2498/cit.1001912

Sažetak
The paper describes a system which enables accurate and easy-to-use contextualized question answering and it provides document overview functionalities. The possibility of asking natural language questions enables a friendly interaction for the user.The contextualization is achieved by using an ontology. The answers are
provided based on a domain specific document collection of choice. The approach consists of several phases as follows: data preparation, data enhancement, data indexing and handling questions. Every module uses state of the art technologies that are shown to work in a complex pipeline to make available question answering on top of a given document repository with the context
of ontologies, such as Cyc, ASFA and WordNet. The functioning of the proposed approach is demonstrated on English document collections on Aquatic Sciences and Fisheries — ASFA, using Cyc ontology, ASFA
thesaurus as domain specific ontology and WordNet as general ontology. Experimental evaluation has shown that the usage of ontologies increases the number of answers retrieved by about 60%. However, the number of answers that are actually correct increases by only 40% when using ontologies.

Ključne riječi
contextualized information retrieval; question answering; ontology

Hrčak ID: 63898

URI
https://hrcak.srce.hr/63898

Posjeta: 1.550 *