arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1908.02938cs.IR
收藏

基于用户反馈的神经文档扩展

Neural Document Expansion with User Feedback

Yue Yin, Chenyan Xiong, Cheng Luo, Zhiyuan Liu

摘要:

本文提出了一种神经文档扩展方法(NeuDEF),丰富了神经排名模型的文档表示。NeuDEF从导致点击文档的查询中获取扩展项,并使用学习到的注意力对这些扩展项进行加权。它被插入到一个标准的神经排名器中,并进行端到端的学习。商业搜索日志上的实验表明,NeuDEF显着提高了最先进的神经排名和扩展方法对不同频率的查询的准确性。进一步的研究显示了点击查询和学习扩展权重的贡献,以及文档流行度对NeuDEF有效性的影响。

英文摘要:

This paper presents a neural document expansion approach (NeuDEF) that enriches document representations for neural ranking models. NeuDEF harvests expansion terms from queries which lead to clicks on the document and weights these expansion terms with learned attention. It is plugged into a standard neural ranker and learned end-to-end. Experiments on a commercial search log demonstrate that NeuDEF significantly improves the accuracy of state-of-the-art neural rankers and expansion methods on queries with different frequencies. Further studies show the contribution of click queries and learned expansion weights, as well as the influence of document popularity of NeuDEF's effectiveness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑