Learning to Rank Complex Semantic Relationships

This paper presents a novel ranking method for complex semantic relationship (semantic association) search based on user preferences. Our method employs a learning-to-rank algorithm to capture each user's preferences. Using this, it automatically constructs a personalized ranking function for the user. The ranking function is then used to sort the results of each subsequent query by the user. Query results that more closely match the user's preferences gain higher ranks. Our method is evaluated using a real-world RDF knowledge base created from Freebase linkedopen-data. The experimental results show that our method significantly improves the ranking quality in terms of capturing user preferences, compared with the state-of-the-art.