报告主题:Integrated Learning of Features and Ranking Function in Information Retrieval

报告专家:聂建云,加拿大蒙特利尔大学 教授




Recently, many deep learning models have been proposed for information retrieval and shown competitive results. They typically aim to learn features either about the contents of the document and the query, or about the interactions between them. However, the existing literature shows that document ranking depends simultaneously on many factors, including both content and interaction features. The integration of both types of neural features has not been extensively studied. In addition, many studies have also shown that the deep neural features cannot replace completely the traditional features, but are complementary. It is thus reasonable to combine deep neural features with traditional features. In this paper, we propose an integrated end-to-end learning framework based on learning-to-rank to learn both neural features and the ranking function simultaneously. The framework also has the flexibility to integrate arbitrary traditional features. Our experiments on public datasets confirm that such an integrated learning strategy is better than separate learning of features and ranking function, and integrating traditional features can further improve the results.



Copyright(c) 2018 All Rights Reserved 版权所有:江西财经大学信息管理学院

地址:江西省南昌市昌北经济技术开发区玉屏大道 邮编:330032