Minimally Supervised Learning of Semantic Knowledge from Query Logs

摘要: We propose a method for learning semantic categories of words with minimal supervision from web search query logs. Our is based on the Espresso algorithm (Pantel and Pennacchiotti, 2006) extracting binary lexical relations, but makes important modifications to handle log data task acquiring categories. present experimental results comparing our two state-ofthe-art minimally supervised knowledge extraction systems using Japanese data, show that achieves higher precision than previously proposed methods. also offers an additional advantage acquisition in Asian language which word segmentation issue, as utilizes no prior segmentation, able harvest new terms correct segmentation.