NTCIR-10

Cross-lingual Link Discovery at NTCIR-10 (CrossLink2)

UKP participated in the Cross-lingual Link Discovery Task (CrossLink-2) at the 10th NTCIR Workshop (NTCIR-10) held on 18-21 June 2013 at the National Center of Sciences in Tokyo, Japan.

CrossLingual Link Discovery (CrossLink) is a task of discovering potential links between cross-lingual documents. Continuing the pilot experiments at NTCIR-9, the tasks at NTCIR-10 was to find valid anchor texts from Wikipedia pages and retrieve corresponding target Wiki pages in another language. At NTCIR-9, the UKP team developed a CrossLink framework consisting of anchor selection, anchor ranking, anchor translation, and target discovery subtasks for English-to-{Chinese, Japanese, Korean} directions. At NTCIR-10, the framework is further extended to work in the reverse direction ({Chinese, Japanese, Korean}-to-English), to find out the properties of the tasks in respect of resources, language pair, language direction as well as link discovery methods and evalution approach.

Details of the task and full results for all systems can be found in the task proceedings. Our system is described in detail in the following paper:

  • Jungi Kim and Iryna Gurevych. UKP at CrossLink2: CJK-to-English Subtasks. In Proceedings of the 10th NTCIR Workshop Meeting on Evaluation of Information Access Technologies: Information Retrieval, Question Answering, and Cross-Lingual Information Access, TBA