arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1904.06808cs.IR
收藏

一种正则化神经排序模型的公理化方法

An Axiomatic Approach to Regularizing Neural Ranking Models

Corby Rosset, Bhaskar Mitra, Chenyan Xiong, Nick Craswell, Xia Song, Saurabh Tiwary

摘要:

公理化信息检索(IR)寻求一组理想的IR模型的原则属性。当正式表达这些属性时,在搜索更好的相关性估计函数时提供指导。神经排序模型通常包含大量参数。这些模型的训练涉及基于大量标记示例搜索适当的参数值。直觉上,可以指导搜索更好的传统IR模型的公理也应该有助于基于机器学习的排名器的更好的参数估计。这项工作探讨了使用IR公理来增强对训练神经排名模型的标记数据的直接监督。我们在训练过程中沿着众所周知的公理修改数据集中的文档,并根据排名模型和公理之间的一致性添加正则化损失,其中文档的版本-原始或扰动-应该是首选的。实验结果表明,公理化正则化后的神经网络排序模型具有更快的收敛速度和更好的泛化能力。

英文摘要:

Axiomatic information retrieval (IR) seeks a set of principle properties desirable in IR models. These properties when formally expressed provide guidance in the search for better relevance estimation functions. Neural ranking models typically contain a large number of parameters. The training of these models involve a search for appropriate parameter values based on large quantities of labeled examples. Intuitively, axioms that can guide the search for better traditional IR models should also help in better parameter estimation for machine learning based rankers. This work explores the use of IR axioms to augment the direct supervision from labeled data for training neural ranking models. We modify the documents in our dataset along the lines of well-known axioms during training and add a regularization loss based on the agreement between the ranking model and the axioms on which version of the document---the original or the perturbed---should be preferred. Our experiments show that the neural ranking model achieves faster convergence and better generalization with axiomatic regularization.

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。

↑