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. |
Year | DOI | Venue |
---|---|---|
2012 | 10.1007/978-3-642-35063-4_35 | WISE |
Keywords | Field | DocType |
search engine query,entity taxonomy,novel method,query segmentation,grammar annotation,entity recognition,search query,query log,ne boundary,search engine result,rich data source | Web search query,Data mining,Annotation,Search engine,Information retrieval,Computer science,Segmentation,Web query classification,Grammar,Named-entity recognition,Semantics | Conference |
Citations | PageRank | References |
5 | 0.51 | 11 |
Authors | ||
3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Areej Alasiry | 1 | 10 | 1.25 |
Mark Levene | 2 | 1272 | 252.84 |
Alexandra Poulovassilis | 3 | 1222 | 370.61 |