DCU at NTCIR-10 Cross-lingual Link Discovery (CrossLink-2) Task
暂无分享,去创建一个
DCU participated in the English to Chinese (C2E) and Chinese to English (C2E) subtasks of the NTCIR 10 CrossLink-2 Cross-lingual Link Discovery (CLLD) task. Our strategy for each query involved extracting potential link anchors as n-gram strings, cleaning of potential anchor strings, and anchor expansion and ranking to select a set of anchors for the query. Potential anchors were translated using Google Translate, and a standard information retrieval technique used to create links between anchors and the top 5 ranked retrieved items selected as potential links for each anchor. We submitted a total of four runs for E2C CLLD and C2E CLLD. We describe our method and results for file-to-file level and anchor-to-file level evaluation.
[1] Andrew Trotman,et al. Overview of the NTCIR-10 Cross-Lingual Link Discovery Task , 2013, NTCIR.
[2] Rada Mihalcea,et al. Wikify!: linking documents to encyclopedic knowledge , 2007, CIKM '07.
[3] Gerhard Weikum,et al. YAGO: A Large Ontology from Wikipedia and WordNet , 2008, J. Web Semant..
[4] Yu-Chun Wang,et al. IISR Crosslink Approach at NTCIR 9 CLLD Task , 2011, NTCIR.
[5] Ian H. Witten,et al. An open-source toolkit for mining Wikipedia , 2013, Artif. Intell..