Paper: Scaling Conditional Random Fields Using Error-Correcting Codes

ACL ID P05-1002
Title Scaling Conditional Random Fields Using Error-Correcting Codes
Venue Annual Meeting of the Association of Computational Linguistics
Session Main Conference
Year 2005
Authors

The paper describes a natural language based expert system route advisor for the public bus transport in Trondheim, Norway. The system is available on the Internet,and has been intstalled at the bus company's web server since the beginning of 1999. The system is bilingual, relying on an internal language independent logic representation. In between the question and the answer is a process of lexical analysis, syntax analysis, semantic analysis, pragmatic reasoning and database query processing. One could argue that the information content could be solved by an interrogation, whereby the customer is asked to produce 4 items: s t a t i o n of departure, station of arrival, earliest departure timeand/or latest arrival time.