Self-Attentive Document Interaction Networks for Permutation Equivariant Ranking
This addresses a gap in information retrieval for learning-to-rank by enabling automatic capture of document interactions without auxiliary information, though it appears incremental as it builds on deep learning and self-attention techniques.
The paper tackles the problem of improving ranking performance by leveraging cross-document interactions in learning-to-rank, proposing a self-attention based network that satisfies permutation-equivariance and scales across varying document set sizes. Experimental results on datasets like Web30k show the methods are more effective and efficient than baselines.
How to leverage cross-document interactions to improve ranking performance is an important topic in information retrieval (IR) research. However, this topic has not been well-studied in the learning-to-rank setting and most of the existing work still treats each document independently while scoring. The recent development of deep learning shows strength in modeling complex relationships across sequences and sets. It thus motivates us to study how to leverage cross-document interactions for learning-to-rank in the deep learning framework. In this paper, we formally define the permutation-equivariance requirement for a scoring function that captures cross-document interactions. We then propose a self-attention based document interaction network and show that it satisfies the permutation-equivariant requirement, and can generate scores for document sets of varying sizes. Our proposed methods can automatically learn to capture document interactions without any auxiliary information, and can scale across large document sets. We conduct experiments on three ranking datasets: the benchmark Web30k, a Gmail search, and a Google Drive Quick Access dataset. Experimental results show that our proposed methods are both more effective and efficient than baselines.