arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2105.12932cs.IRcs.CL
收藏

对比微调提高神经排序器的鲁棒性

Contrastive Fine-tuning Improves Robustness for Neural Rankers

AWS AI Labs(亚马逊云科技人工智能实验室)

Xiaofei Ma, Cicero Nogueira dos Santos, Andrew O. Arnold

摘要:

当暴露于噪声输入或应用于新领域时,最先进的神经排序器的性能可能会大幅恶化。在本文中,我们提出了一种新的方法微调神经排名,可以显着提高其鲁棒性域外数据和查询扰动。具体来说,在微调期间,将比较表示空间中的数据点的对比损失与标准排名损失相结合。我们使用相关性标签来表示相似/不相似对,这使得模型能够学习不同查询-文档对之间的底层匹配语义,并提高鲁棒性。在四个通道的排名数据集的实验中,所提出的对比微调方法获得的鲁棒性的查询重新制定,噪声扰动,和zero-shot传输的BERT和BART基于排名的改进。此外,我们的实验表明,对比微调优于数据增强的鲁棒神经排名。

英文摘要:

The performance of state-of-the-art neural rankers can deteriorate substantially when exposed to noisy inputs or applied to a new domain. In this paper, we present a novel method for fine-tuning neural rankers that can significantly improve their robustness to out-of-domain data and query perturbations. Specifically, a contrastive loss that compares data points in the representation space is combined with the standard ranking loss during fine-tuning. We use relevance labels to denote similar/dissimilar pairs, which allows the model to learn the underlying matching semantics across different query-document pairs and leads to improved robustness. In experiments with four passage ranking datasets, the proposed contrastive fine-tuning method obtains improvements on robustness to query reformulations, noise perturbations, and zero-shot transfer for both BERT and BART based rankers. Additionally, our experiments show that contrastive fine-tuning outperforms data augmentation for robustifying neural rankers.

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。

↑