Question-answering by predictive annotation
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Exploiting redundancy in question answering
Proceedings of the 24th annual international ACM SIGIR conference on Research and development in information retrieval
Machine Learning
Slot Grammar: A System for Simpler Construction of Practical Natural Language Grammars
Proceedings of the International Symposium on Natural Language and Logic
FAQ finder: a case-based approach to knowledge navigation
CAIA '95 Proceedings of the 11th Conference on Artificial Intelligence for Applications
Disambiguation of proper names in text
ANLC '97 Proceedings of the fifth conference on Applied natural language processing
Alternative phrases and natural language information retrieval
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
The role of lexico-semantic feedback in open-domain textual question-answering
ACL '01 Proceedings of the 39th Annual Meeting on Association for Computational Linguistics
Question answering using maximum entropy components
NAACL '01 Proceedings of the second meeting of the North American Chapter of the Association for Computational Linguistics on Language technologies
Automatic categorization of query results
SIGMOD '04 Proceedings of the 2004 ACM SIGMOD international conference on Management of data
NaLIX: A generic natural language search environment for XML data
ACM Transactions on Database Systems (TODS)
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Constructing a generic natural language interface for an XML database
EDBT'06 Proceedings of the 10th international conference on Advances in Database Technology
Term disambiguation in natural language query for XML
FQAS'06 Proceedings of the 7th international conference on Flexible Query Answering Systems
| Hi-index | 0.00 |
We describe a hybrid approach to improving search performance by providing a natural language front end to a traditional keyword-based search engine. The key component of the system is iterative query formulation and retrieval, in which one or more queries are automatically formulated from the user's question, issued to the search engine, and the results accumulated to form the hit list. New queries are generated by relaxing previously-issued queries using transformation rules, applied in an order obtained by reinforcement learning. This statistical component is augmented by a knowledge-driven hub-page identifier that retrieves a hub-page for the most salient noun phrase in the question, if possible. Evaluation on an unseen test set over the www.ibm.com public website with 1.3 million webpages shows that both components make substantial contribution to improving search performance, achieving a combined 137% relative improvement in the number of questions correctly answered, compared to a baseline of keyword queries consisting of two noun phrases.