Improving automatic query expansion
Proceedings of the 21st annual international ACM SIGIR conference on Research and development in information retrieval
Term Weighting in Information Retrieval Using the Term Precision Model
Journal of the ACM (JACM)
Interactive Internet search: keyword, directory and query reformulation mechanisms compared
SIGIR '00 Proceedings of the 23rd annual international ACM SIGIR conference on Research and development in information retrieval
Placing search in context: the concept revisited
ACM Transactions on Information Systems (TOIS)
Understanding user goals in web search
Proceedings of the 13th international conference on World Wide Web
Context-sensitive information retrieval using implicit feedback
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Personalizing search via automated analysis of interests and activities
Proceedings of the 28th annual international ACM SIGIR conference on Research and development in information retrieval
Proceedings of the 15th international conference on World Wide Web
InfoScale '06 Proceedings of the 1st international conference on Scalable information systems
ICTD'09 Proceedings of the 3rd international conference on Information and communication technologies and development
Characterizing the transport behaviour of the short message service
Proceedings of the 8th international conference on Mobile systems, applications, and services
Where the streets have no name: experiences in GIR for a developing country
Proceedings of the 7th Workshop on Geographic Information Retrieval
| Hi-index | 0.00 |
SMS-based web search is different from traditional web search in that the final response to a search query is limited to a very small number of bytes (typically 1-2 SMS messages, 140 bytes each). SMS-based web search is also a non-interactive search problem where the user has to specify a query and obtain a response in one round of search. Enabling search with with such constraints is challenging. Several search engines have developed SMS-based search capabilities in recent years and many of these search engines are limited in their recognized topics (phone, address, location, weather etc.), involve a human in the loop or apply to only specific types of search queries. We describe a simple generic approach to extracting results for both well-known and arbitrary topics. We have implemented our prototype system SMSFind and demonstrate the effectiveness of our approach. While the underlying mechanisms we present are by no means perfect, we show that our system returns appropriate responses for a range of topics not covered by existing systems.