Intelligent Time-Aware Query Translation for Text Sources

Time-stamped documents such as newswire articles, blog posts and other web-pages are often archived online. Since these archives cover long spans of time, the terminology in them could undergo significant evolution. In answering user queries over such text, it is desirable that the system be intelligent enough to incorporate historical information. For example, a query on Sri Lanka should automatically retrieve documents with its former name Ceylon. Hence, temporal terminology evolution needs to be taken into account to translate these queries. This has become vital today because users expect that computer systems have the intelligence to find all related information pertaining to their queries. In this research we attempt to discover such concepts that evolve over time and use those discovered concepts to provide time-aware responses to user queries. Our solution and evaluation are summarized in the paper.