Abstract
Question focus extraction is one of the key of question analysis in a question answering system. This paper presents a simple model (Fk-BRNN) based on bidirectional recurrent neural network (BRNN) for question focus extraction, and applies it to a Chinese Airport Question Answering (CAQA) system. The Fk-BRNN model memorizes different sentence patterns and the focus positions in each sentence pattern, then it extracts focus words at the corresponding positions according to different sentence patterns. For a question, the Fk-BRNN model can extract not only one or more known focus words with correct semantics, but also unknown new focus words. So it can greatly reduce the size of training corpus, and keep excellent generalization ability. As a result, it is more practical and suitable for online learning system. Based on the above ideas, this paper designs and implements a CAQA system, which can accurately answer the questions with a superior performance according to our experimental results.
Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
