Extraction and evaluation of candidate named entities in search engine queries

Authors:
Areej Alasiry;Mark Levene;Alexandra Poulovassilis
Affiliations:
Birkbeck, University of London, London, United Kingdom;Birkbeck, University of London, London, United Kingdom;Birkbeck, University of London, London, United Kingdom
Venue:
WISE'12 Proceedings of the 13th international conference on Web Information Systems Engineering
Year:
2012

Citing 9
Cited 0

Weakly-supervised discovery of named entities using web search queries

Proceedings of the sixteenth ACM conference on Conference on information and knowledge management
Open information extraction from the web

Communications of the ACM - Surviving the data deluge
Named entity recognition in query

Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
DBpedia - A crystallization point for the Web of Data

Web Semantics: Science, Services and Agents on the World Wide Web
Building taxonomy of web search intents for name entity queries

Proceedings of the 19th international conference on World wide web
Using search session context for named entity recognition in query

Proceedings of the 33rd international ACM SIGIR conference on Research and development in information retrieval
Domain-independent entity extraction from web search query logs

Proceedings of the 20th international conference companion on World wide web
Query segmentation revisited

Proceedings of the 20th international conference on World wide web
Joint annotation of search queries

HLT '11 Proceedings of the 49th Annual Meeting of the Association for Computational Linguistics: Human Language Technologies - Volume 1

Quantified Score

Hi-index	0.00

Visualization

Abstract

Named Entity Recognition (NER) has recently been applied to search queries, in order to better understand their semantics. We present a novel method for detecting candidate named entities (NEs) using grammar annotation and query segmentation with the aid of top-n snippets from search engine results, and a web n-gram model to accurately identify NE boundaries. We then evaluate this method automatically using DBpedia as a rich data source of NEs, with the aid of a small representative random sample that is manually annotated. Finally, an analysis of the types of named entities that often occur in a query log is conducted, from which a search query driven named entity taxonomy is presented.