Senior Search Consultant
Rajani's background is in design and engineering of large scale search and analytics systems, specializing in information retrieval and machine learning topics.
Rajani Maski is speaking at the following session/s
Reduce Query Time up to 60% with Selective Search
Google has set high standards in terms of quality results and swift response. In an attempt to meet those benchmarks, this talk will present a technique to improve search relevance and query performance by dividing collections into topic shards. This will reduce query time up to 60% while maintaining the quality of search results. Currently, solr offers two types of sharding: "implicit" & "composite", the latter aims to uniformly divide collections into shards and requires search across every shard whereas "implicit" allows the client to decide which shard a document should be routed to. Employing the “implicit” type, documents are routed to shards based on content analogy. This divides the collection into subject shards and search is exclusively executed across ranked shards. This concept is based on cluster hypothesis which states documents in the same cluster behave similarly wrt relevance to information needs, and this is researched in academics by Kulkarni A, Callan J as Selective Search.
This talk will outline the latest search techniques, present the experimental setup and conclude with evident empirical results.
Experienced Search and ML engineers or understanding of Fusion AI server. Expect audience to know concepts of ML and Distributed Search.