The effect of adding relevance information in a relevance feedback environment
SIGIR '94 Proceedings of the 17th annual international ACM SIGIR conference on Research and development in information retrieval
Scaling question answering to the web
ACM Transactions on Information Systems (TOIS)
A Contextual Term Suggestion Mechanism for Interactive Web Search
WI '01 Proceedings of the First Asia-Pacific Conference on Web Intelligence: Research and Development
Experiments with open-domain textual Question Answering
COLING '00 Proceedings of the 18th conference on Computational linguistics - Volume 1
Proceedings of the 4th ACM/IEEE-CS joint conference on Digital libraries
Learning surface text patterns for a Question Answering system
ACL '02 Proceedings of the 40th Annual Meeting on Association for Computational Linguistics
| Hi-index | 0.00 |
In Online Inquiry-Based Learning (OIBL) learners search for information to answer driving questions. While learners conduct sequential related searches, the search engines interpret each query in isolation, and thus are unable to utilize task context. Consequently, learners usually get less relevant search results. We are developing a NLP-based search agent to bridge the gap between learners and search engines. Our algorithms utilize contextual features to provide user with search term suggestions and results re-ranking. Our pilot study indicates that our method can effectively enhance the quality of OIBL.