Title :
Sentence level fact based search engine: News Fact Finder
Author :
Ribeiro, Cristina ; Salmon, Ricardo ; Amarala, Swathi ; Hamada, Christina
Author_Institution :
Comput. Sci., Univ. of Waterloo, Waterloo, ON, Canada
Abstract :
Users searching the Internet for news are not able to find relevant fact-based results for certain queries using the major search engines. Queries that require exact substring matching in order to obtain very relevant results are not currently possible. Furthermore, search engines do not discriminate in returning results that are opinions and not quantifiable facts. Our sentence level search engine, News Fact Finder, is designed using suffix arrays, filters out opinions, and produces very relevant results that are attractive to users. The News Fact Finder produces a 73% success rate of providing relevant fact based results.
Keywords :
Internet; query processing; relevance feedback; search engines; Internet; news fact finder; sentence level fact based search engine; substring matching; suffix array; Arrays; Computer science; Indexes; Information services; Internet; Search engines; Web sites; Heuristic Optimization and Search; Natural Language Processing; Sentence Level Search Engine; Suffix Arrays;
Conference_Titel :
Information Reuse and Integration (IRI), 2010 IEEE International Conference on
Conference_Location :
Las Vegas, NV
Print_ISBN :
978-1-4244-8097-5
DOI :
10.1109/IRI.2010.5558906
