Matches in SemOpenAlex for { <https://semopenalex.org/work/W2614327962> ?p ?o ?g. }
Showing items 1 to 93 of
93
with 100 items per page.
- W2614327962 endingPage "150" @default.
- W2614327962 startingPage "136" @default.
- W2614327962 abstract "Search diversification (also called diversity search), is an important approach to tackling the query ambiguity problem in information retrieval. It aims to diversify the search results that are originally ranked according to their probabilities of relevance to a given query, by re-ranking them to cover as many as possible different aspects (or subtopics) of the query. Most existing diversity search models heuristically balance the relevance ranking and the diversity ranking, yet lacking an efficient learning mechanism to reach an optimized parameter setting. To address this problem, we propose a learning-to-diversify approach which can directly optimize the search diversification performance (in term of any effectiveness metric). We first extend the ranking function of a widely used learning-to-rank framework, i.e., LambdaMART, so that the extended ranking function can correlate relevance and diversity indicators. Furthermore, we develop an effective learning algorithm, namely Document Repulsion Model (DRM), to train the ranking function based on a Document Repulsion Theory (DRT). DRT assumes that two result documents covering similar query aspects (i.e., subtopics) should be mutually repulsive, for the purpose of search diversification. Accordingly, the proposed DRM exerts a repulsion force between each pair of similar documents in the learning process, and includes the diversity effectiveness metric to be optimized as part of the loss function. Although there have been existing learning based diversity search methods, they often involve an iterative sequential selection process in the ranking process, which is computationally complex and time consuming for training, while our proposed learning strategy can largely reduce the time cost. Extensive experiments are conducted on the TREC diversity track data (2009, 2010 and 2011). The results demonstrate that our model significantly outperforms a number of baselines in terms of effectiveness and robustness. Further, an efficiency analysis shows that the proposed DRM has a lower computational complexity than the state of the art learning-to-diversify methods." @default.
- W2614327962 created "2017-05-26" @default.
- W2614327962 creator A5003817752 @default.
- W2614327962 creator A5028538133 @default.
- W2614327962 creator A5029360035 @default.
- W2614327962 creator A5050532724 @default.
- W2614327962 creator A5057282504 @default.
- W2614327962 date "2017-10-01" @default.
- W2614327962 modified "2023-10-16" @default.
- W2614327962 title "Learning to diversify web search results with a Document Repulsion Model" @default.
- W2614327962 cites W1990313671 @default.
- W2614327962 cites W2002379171 @default.
- W2614327962 cites W2007815473 @default.
- W2614327962 cites W2048045485 @default.
- W2614327962 cites W2162059449 @default.
- W2614327962 cites W4206671592 @default.
- W2614327962 doi "https://doi.org/10.1016/j.ins.2017.05.027" @default.
- W2614327962 hasPublicationYear "2017" @default.
- W2614327962 type Work @default.
- W2614327962 sameAs 2614327962 @default.
- W2614327962 citedByCount "6" @default.
- W2614327962 countsByYear W26143279622018 @default.
- W2614327962 countsByYear W26143279622019 @default.
- W2614327962 countsByYear W26143279622020 @default.
- W2614327962 countsByYear W26143279622022 @default.
- W2614327962 crossrefType "journal-article" @default.
- W2614327962 hasAuthorship W2614327962A5003817752 @default.
- W2614327962 hasAuthorship W2614327962A5028538133 @default.
- W2614327962 hasAuthorship W2614327962A5029360035 @default.
- W2614327962 hasAuthorship W2614327962A5050532724 @default.
- W2614327962 hasAuthorship W2614327962A5057282504 @default.
- W2614327962 hasBestOaLocation W26143279622 @default.
- W2614327962 hasConcept C119857082 @default.
- W2614327962 hasConcept C124975894 @default.
- W2614327962 hasConcept C14036430 @default.
- W2614327962 hasConcept C144133560 @default.
- W2614327962 hasConcept C154945302 @default.
- W2614327962 hasConcept C158154518 @default.
- W2614327962 hasConcept C162324750 @default.
- W2614327962 hasConcept C162853370 @default.
- W2614327962 hasConcept C176217482 @default.
- W2614327962 hasConcept C17744445 @default.
- W2614327962 hasConcept C180916674 @default.
- W2614327962 hasConcept C189430467 @default.
- W2614327962 hasConcept C199539241 @default.
- W2614327962 hasConcept C21547014 @default.
- W2614327962 hasConcept C23123220 @default.
- W2614327962 hasConcept C41008148 @default.
- W2614327962 hasConcept C78458016 @default.
- W2614327962 hasConcept C86037889 @default.
- W2614327962 hasConcept C86803240 @default.
- W2614327962 hasConceptScore W2614327962C119857082 @default.
- W2614327962 hasConceptScore W2614327962C124975894 @default.
- W2614327962 hasConceptScore W2614327962C14036430 @default.
- W2614327962 hasConceptScore W2614327962C144133560 @default.
- W2614327962 hasConceptScore W2614327962C154945302 @default.
- W2614327962 hasConceptScore W2614327962C158154518 @default.
- W2614327962 hasConceptScore W2614327962C162324750 @default.
- W2614327962 hasConceptScore W2614327962C162853370 @default.
- W2614327962 hasConceptScore W2614327962C176217482 @default.
- W2614327962 hasConceptScore W2614327962C17744445 @default.
- W2614327962 hasConceptScore W2614327962C180916674 @default.
- W2614327962 hasConceptScore W2614327962C189430467 @default.
- W2614327962 hasConceptScore W2614327962C199539241 @default.
- W2614327962 hasConceptScore W2614327962C21547014 @default.
- W2614327962 hasConceptScore W2614327962C23123220 @default.
- W2614327962 hasConceptScore W2614327962C41008148 @default.
- W2614327962 hasConceptScore W2614327962C78458016 @default.
- W2614327962 hasConceptScore W2614327962C86037889 @default.
- W2614327962 hasConceptScore W2614327962C86803240 @default.
- W2614327962 hasFunder F4320321001 @default.
- W2614327962 hasFunder F4320335254 @default.
- W2614327962 hasLocation W26143279621 @default.
- W2614327962 hasLocation W26143279622 @default.
- W2614327962 hasOpenAccess W2614327962 @default.
- W2614327962 hasPrimaryLocation W26143279621 @default.
- W2614327962 hasRelatedWork W104148947 @default.
- W2614327962 hasRelatedWork W109267858 @default.
- W2614327962 hasRelatedWork W1528738305 @default.
- W2614327962 hasRelatedWork W1976758266 @default.
- W2614327962 hasRelatedWork W2031812225 @default.
- W2614327962 hasRelatedWork W2041353081 @default.
- W2614327962 hasRelatedWork W2122040421 @default.
- W2614327962 hasRelatedWork W2967976110 @default.
- W2614327962 hasRelatedWork W3094569813 @default.
- W2614327962 hasRelatedWork W4385565564 @default.
- W2614327962 hasVolume "411" @default.
- W2614327962 isParatext "false" @default.
- W2614327962 isRetracted "false" @default.
- W2614327962 magId "2614327962" @default.
- W2614327962 workType "article" @default.