2026-05-01T10:31:59Z https://meral.edu.mm/oai

oai:meral.edu.mm:recid/4484 2021-12-13T02:00:05Z 1582963302567:1597824273898 user-ucsy

Query Dependent Ranking based on PCA-based Query Representation Lwin, Pwint Hay Mar Kham, Nang Saing Moon Ranking is a crucial part of informationretrieval. Queries describe the users’ searchintent and therefore they play an essential role inthe context of ranking for information retrieval.The diverse feature impacts on ranking relevancewith respect to different queries. This papertends to consider query difference in learningranking function by clustering the queries whereeach query cluster represents a group of querieswhich have the similar set of important featuresfor measuring ranking relevance. The success ofclustering usually depends on the representationof the data. The query features are generatedbased on the ranking features values of querydocument pair and Principal ComponentAnalysis (PCA) is used to construct therepresentation of query. To cluster the queries,bisecting k-means clustering algorithm is used.RankSVM algorithm is used for modelconstruction. 2012-02-28 http://hdl.handle.net/20.500.12678/0000004484 https://meral.edu.mm/records/4484