File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Conference Paper: KB-enabled query recommendation for long-tail queries

TitleKB-enabled query recommendation for long-tail queries
Authors
Issue Date2016
PublisherACM.
Citation
The 25th ACM International Conference on Information and Knowledge Management (CIKM), Indianapolis, IN., 24-28 October 2016. In Conference Proceedings, 2016, p. 1-6 How to Cite?
AbstractIn recent years, query recommendation algorithms have been designed to provide related queries for search engine users. Most of these solutions, which perform extensive analysis of users’ search history (or query logs), are largely insufficient for long-tail queries that rarely appear in query logs. To handle such queries, we study a new solution, which makes use of a knowledge base (or KB), such as YAGO and Freebase. A KB is a rich information source that describes how real-world entities are connected. We extract entities from a query, and use these entities to explore new ones in the KB. Those discovered entities are then used to suggest new queries to the user. As shown in our experiments, our approach provides better recommendation results for long-tail queries than existing solutions.
Persistent Identifierhttp://hdl.handle.net/10722/232182
ISBN

 

DC FieldValueLanguage
dc.contributor.authorHuang, Z-
dc.contributor.authorCautis, B-
dc.contributor.authorCheng, R-
dc.contributor.authorZheng, Y-
dc.date.accessioned2016-09-20T05:28:17Z-
dc.date.available2016-09-20T05:28:17Z-
dc.date.issued2016-
dc.identifier.citationThe 25th ACM International Conference on Information and Knowledge Management (CIKM), Indianapolis, IN., 24-28 October 2016. In Conference Proceedings, 2016, p. 1-6-
dc.identifier.isbn978-1-4503-4073-1-
dc.identifier.urihttp://hdl.handle.net/10722/232182-
dc.description.abstractIn recent years, query recommendation algorithms have been designed to provide related queries for search engine users. Most of these solutions, which perform extensive analysis of users’ search history (or query logs), are largely insufficient for long-tail queries that rarely appear in query logs. To handle such queries, we study a new solution, which makes use of a knowledge base (or KB), such as YAGO and Freebase. A KB is a rich information source that describes how real-world entities are connected. We extract entities from a query, and use these entities to explore new ones in the KB. Those discovered entities are then used to suggest new queries to the user. As shown in our experiments, our approach provides better recommendation results for long-tail queries than existing solutions.-
dc.languageeng-
dc.publisherACM.-
dc.relation.ispartofConference on Information and Knowledge Management, CIKM 2016 Proceedings-
dc.titleKB-enabled query recommendation for long-tail queries-
dc.typeConference_Paper-
dc.identifier.emailCheng, R: ckcheng@cs.hku.hk-
dc.identifier.authorityCheng, R=rp00074-
dc.identifier.doi10.1145/2983323.2983650-
dc.identifier.hkuros265240-
dc.identifier.spage1-
dc.identifier.epage6-
dc.publisher.placeUnited States-
dc.customcontrol.immutablesml 161026-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats