arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 0704.3359cs.IRcs.AI
收藏

排序测度的直接优化

Direct Optimization of Ranking Measures

Max Planck Institute for Biological Cybernetics(马克斯·普朗克生物控制论研究所);NICTA(澳大利亚国家信息与通信技术研究院);ANU(澳大利亚国立大学)

Quoc Le, Alexander Smola

摘要:

网页排名和协同过滤需要优化复杂的性能指标。目前的支持向量方法无法直接优化它们,而是专注于成对比较。我们提出了一种新的方法,允许直接优化相关的损失函数。这是通过希尔伯特空间中的结构化估计来实现的。它是最相关的最大边际马尔可夫网络优化的多元性能指标。我们的方法的关键是,在训练过程中,排名问题可以被视为一个线性分配问题,可以通过匈牙利婚姻算法来解决。在测试时,排序操作就足够了,因为我们的算法为每个(文档,查询)对分配了一个相关性分数。实验结果表明,该算法速度快,效果良好.

英文摘要:

Web page ranking and collaborative filtering require the optimization of sophisticated performance measures. Current Support Vector approaches are unable to optimize them directly and focus on pairwise comparisons instead. We present a new approach which allows direct optimization of the relevant loss functions. This is achieved via structured estimation in Hilbert spaces. It is most related to Max-Margin-Markov networks optimization of multivariate performance measures. Key to our approach is that during training the ranking problem can be viewed as a linear assignment problem, which can be solved by the Hungarian Marriage algorithm. At test time, a sort operation is sufficient, as our algorithm assigns a relevance score to every (document, query) pair. Experiments show that the our algorithm is fast and that it works very well.

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。

↑