The majority of recent Cross-Language Information Retrieval (CLIR) research has focused on European languages. CLIR problems that involve East Asian languages such as Chinese introduce additional challenges, because written Chinese texts lack boundaries between terms. This paper examines three Chinese segmentation techniques in combination with two variants of dictionary-based Chinese to English query translation. The results indicate that failure to segment terms, particularly technical terms and names, can have a cascading effect that reduces retrieval effectiveness. Task-tuned segmentation algorithms and alternative term weighting strategies are suggested as productive directions for future work.
Douglas W. Oard, Jianqiang Wang