Calais (Reuters product)
Calais is a service by Thomson Reuters that automatically extracts semantic information from web pages in a format that can be used on the semantic web.[1] Calais was launched in January 2008, and is free to use.[2][3]
The Calais Web service reads unstructured text and returns Resource Description Framework formatted results identifying entities, facts and events within the text.[4] The service appears to be based on technology acquired when Reuters purchased ClearForest in 2007.[5]
The technology has also been used to automatically tag blog articles[6] and organize museum collections.[7]
Calais uses natural language processing technologies delivered via a web service interface.
References
- "Calais Overview". Archived from the original on 2008-10-24. Retrieved 2008-10-24.
- "Reuters Wants The World To Be Tagged". Archived from the original on 2008-04-11. Retrieved 2008-04-12.
- Start making sense
- "Calais API guide". Archived from the original on 2008-10-23. Retrieved 2008-10-24.
- "ClearForest". Archived from the original on 2013-01-24. Retrieved 2012-11-27.
- WP Calais Auto Tagger
- OpenCalais meets our museum collection /auto-tagging and semantic parsing of collection data
External links
- Official website
- Curry, E.; Freitas, A.; O’Riáin, S. (2010). "The Role of Community-Driven Data Curation for Enterprises" (PDF). In Wood, D. (ed.). Linking Enterprise Data. Preprint. Boston, MA: Springer US. pp. 25–47. doi:10.1007/978-1-4419-7665-9. ISBN 978-1441976642.
Case Study of Open Calais
This article is issued from Wikipedia. The text is licensed under Creative Commons - Attribution - Sharealike. Additional terms may apply for the media files.