prikaz prve stranice dokumenta Modeli rangiranja po svježini za pretraživanje weba
No public access
master's thesis
Modeli rangiranja po svježini za pretraživanje weba
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:253356
Gombar, Paula
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Gombar, P. (2018). Modeli rangiranja po svježini za pretraživanje weba (Master's thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:253356

Gombar, Paula. "Modeli rangiranja po svježini za pretraživanje weba." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:253356

Gombar, Paula. "Modeli rangiranja po svježini za pretraživanje weba." Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:253356

Gombar, P. (2018). 'Modeli rangiranja po svježini za pretraživanje weba', Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 27 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:253356

Gombar P. Modeli rangiranja po svježini za pretraživanje weba [Master's thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 December 27] Available at: https://urn.nsk.hr/urn:nbn:hr:168:253356

P. Gombar, "Modeli rangiranja po svježini za pretraživanje weba", Master's thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:253356

Metadata
TitleModeli rangiranja po svježini za pretraživanje weba
Title (english)Recency Ranking Models for Web Search
AuthorPaula Gombar
MentorJan Šnajder (mentor)
Committee memberJan Šnajder (predsjednik povjerenstva)
Committee memberMarko Čupić (član povjerenstva)
Committee memberBojana Dalbelo-Bašić (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-17, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Computing
Abstract
Porastom raspoloživih količina dostupnih informacija na Webu, povećalo se zanimanje za sustavima koji dohvaćaju informacije, poput sustava za pretraživanje. Korisnost sustava za pretraživanje ovisi o relevantnosti dohvaćenih rezultata. Većina sustava za pretraživanje koriste metode rangiranja rezultata kako bi pružili najbolje rezultate na vrhu. Pri pretraživanju weba, rangiranje po svježini odnosi se na rangiranje dokumenata s obzirom na vrijeme njihovog nastanka. Svježina rezultata vrlo je bitna kod modernog pretraživanja Weba. Nemogućnost prepoznavanja temporalnog aspekta upita može biti pogubna za iskustvo korisnika i predstaviti sustav za pretraživanje ustajalim. Efikasno kombiniranje vremenskih značajki i značajki za relevantnost dokumenata u sklopu sustava za rangiranje je i dalje otvoreno pitanje u znanstvenoj zajednici. U okviru diplomskog rada potrebno je proučiti postupke za rangiranje po svježini pri pretraživanju Weba s naglaskom na postupke temeljene na strojnom učenju. Razraditi sustav za dohvaćanje informacija koji prepoznaje i reagira na upite osjetljive na aktualna događanja koristeći model za rangiranje temeljen na strojnom učenju, po uzoru na rad Dong i dr. (2010). Izgraditi i označiti odgovarajući skup podataka koji se sastoji od parova upit-dokument za razvoj i ispitivanje modela. Provesti iscrpno eksperimentalno vrednovanje modela, statističku obradu rezultata te analizu pogrešaka.
Abstract (english)
Given the increase in the amount of accessible information on the web, more attention has been drawn to information retrieval systems, such as search engines. The usefulness of a search engine depends on the relevance of the result set it gives back. Most search engines employ methods to rank the results to provide the best results first. In web search, recency ranking refers to ranking documents by relevance which takes freshness into account. The freshness of the results is important in modern web search. Failing to recognize the temporal aspect of a query can negatively affect the user experience, and make the search engine appear stale. Effectively combining temporal features, as well as relevance-sensitive features in a ranking framework is still an open question for the research community. This paper examines methods for recency ranking in web search with a special focus on methods based on machine learning. A retrieval system which detects and responds to recency sensitive queries by using a machine learned ranking model is proposed. This system is based on the work described in Dong, et al. (2010). An appropriate dataset of query-document pairs is to be built and annotated in order to develop and test the system. An exhaustive experimental evaluation of the model is to be conducted, along with statistical result and error analysis.
Keywords
Keywords (english)
Languageenglish
URN:NBNurn:nbn:hr:168:253356
Study programmeTitle: Computing
Study programme type: university
Study level: graduate
Academic / professional title: magistar/magistra inženjer/inženjerka računarstva (magistar/magistra inženjer/inženjerka računarstva)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 20:31:09