Towards an Understanding of Entity-Oriented Search Intents

Date: March 30, 2018
Venue: Grenoble, France. The 40th European Conference on Information Retrieval (ECIR '18)
Corresponding article: https://arxiv.org/abs/1802.08010

Please cite the paper, and link to or credit this presentation when using it or part of it in your work.

#InformationRetrieval #IR #EntityOrientedSearch #EntityOrientedSearchIntents #KnowledgeBases

Transcript

1. TOWARDS AN UNDERSTANDING OF ENTITY-ORIENTED SEARCH INTENTS Darío Garigliotti and Krisztian Balog University of Stavanger Get the paper http://bit.ly/ecir2018-intents RESULTS organization business operation chemical compound film location event food hotel disease restaurant travel destination 0 50 100 150 200 250 university house person newspaper airport basketball player album professional sports team game artwork 0 50 100 150 200 railway human language tv station political party amusement park exhibition venue chef programming language academic institution netflix genre 0 20 40 60 80 100 120 war currency blogger hobby football match sports championship star muscle olympic sport company 0 10 20 30 40 50 WroSicaO cycOone kingdoP PedicaO sSeciaOWy coPic book SubOisher oiO fieOd Wower beer counWry region eOecWion asWeroid beOief 0 10 20 30 40 50 3roSerWy WebsiWe Service 2Wher Property: 28.6% Service: 54.06% Website: 5.34% Other: 12.08% • RQ: What do entity-oriented queries ask for? - Which searches can be fulfilled with answers from a knowledge base? - Which searches would require to interact with external services? What are prominent entity-oriented search intents, and how can they be fulfilled? INTENT CATEGORIZATION SCHEME Choose your class: Property Website Service Other <tower> height <company> ceo <restaurant> yelp <person> instagram <travel destination> things to do <album> zip download <company> india <tower> collapse TYPE-LEVEL QUERY PATTERNS • Approach for building the collection: - Pick a Freebase type if it covers 100+ prominent entities - Get query suggestions for top 1000- entities per type - For each query, replace entity by type - Aggregate all frequencies for each (type, refiner) pair - Filter out all type-level refiners with frequency of 4- - Select 50 representative types by stratified sampling - Annotate 2.3K+ unique type-level refiners with intent category by 3+ judges via crowdsourcing • Type-level patterns of entity-oriented queries: <city> restaurants with a view entity type entity refiner grenoble restaurants with a view