Document Type
Conference Paper
Publication Date
9-9-2010
Keywords
heuristic optimization and search, sentence level search engine, suffix arrays, natural language processing
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.
Faculty
Faculty of Applied Science & Technology (FAST)
Journal
IEEE International Conference on Information Reuse & Integration
First Page
368
Last Page
373
Copyright
© Cristina Ribeiro, Ricardo Salmon, Swathi Amarala, Christina Hamada
Terms of Use
Terms of Use for Works posted in SOURCE.
Creative Commons License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.
Original Publication Citation
Ribeiro, C., Salmon, R., Amarala,S. & Hamada, C. (2010, September, 9). Sentence level fact based search engine: news fact finder. 2010 IEEE International Conference on Information Reuse and Integration, IRI 2010. 368 - 373. 10.1109/IRI.2010.5558906
SOURCE Citation
Ribeiro, Cristina; Salmon, Ricardo; Amarala, Swathi; and Hamada, Christina, "Sentence Level Fact Based Search Engine: News Fact Finder" (2010). Publications and Scholarship. 54.
https://source.sheridancollege.ca/fast_publications/54
