Term Distillation for Cross-DB Retrieval

In cross-DB retrieval, the domain of queries differs from the retrieval target in the distribution of that of term occurrences. This causes incorrect term weighting in the retrieval system which assigns to each term a retrieval weight based on the distribution of term occurrences. To resolve the problem, we propose \term distillation" which is a framework for query term selection in crossDB retrieval. The experiments using the NTCIR patent retrieval test collection demonstrate that term distillation is e ective for cross-DB retrieval.