ACM Transactions on Information Systems (TOIS)
Improving search relevance for implicitly temporal queries
Proceedings of the 32nd international ACM SIGIR conference on Research and development in information retrieval
Clustering and exploring search results using timeline constructions
Proceedings of the 18th ACM conference on Information and knowledge management
A language modeling approach for temporal information needs
ECIR'2010 Proceedings of the 32nd European conference on Advances in Information Retrieval
How fresh do you want your search results?
Proceedings of the 22nd ACM international conference on Conference on information & knowledge management
| Hi-index | 0.00 |
The World Wide Web (WWW) is a huge information network from which retrieving and organizing quality relevant content remains an open question for mostly all ambiguous queries. As an example, many queries have temporal implicit intents associated with them but they are not inferred by search engines. Inferring the user intentions and the period he has in mind, may therefore play an extremely important role in the improvement of the results. Our work goes in this direction. We aim to introduce a temporal analysis framework for analyzing documents in a temporal dimension in order to identify and understand the temporal nature of any given query, namely implicit ones. Our analysis is not based on metadata, but on the exploitation of temporal information from the content itself, particularly within web snippets, which are interesting pieces of concentrated information, where time clues, especially years, often appear. Our intention is to develop a language-independent solution and to model the degree of relationship between the terms and dates identified. This is the core part of the framework and the basis for both temporal query understanding and search results exploration, such as temporal clustering. We believe that inferring this knowledge is a very important step in the process of adding a temporal dimension to IR systems, thus disambiguating a large class of queries for which search engines continue to fail.