Neural Ranking Models with Multiple Document Fields

TL;DR

This paper presents a neural ranking model that effectively utilizes multiple document fields, including variable-length and missing data, to improve ad-hoc retrieval performance over traditional and simpler neural models.

Contribution

It introduces a novel neural model capable of handling multiple, variable-length, and missing document fields with masking and dropout techniques, outperforming existing methods.

Findings

Model outperforms baseline methods including BM25F.

Handling multiple fields improves retrieval accuracy.

Techniques effectively manage missing and variable-length data.

Abstract

Deep neural networks have recently shown promise in the ad-hoc retrieval task. However, such models have often been based on one field of the document, for example considering document title only or document body only. Since in practice documents typically have multiple fields, and given that non-neural ranking models such as BM25F have been developed to take advantage of document structure, this paper investigates how neural models can deal with multiple document fields. We introduce a model that can consume short text fields such as document title and long text fields such as document body. It can also handle multi-instance fields with variable number of instances, for example where each document has zero or more instances of incoming anchor text. Since fields vary in coverage and quality, we introduce a masking method to handle missing field instances, as well as a field-level dropout method to avoid relying too much on any one field. As in the studies of non-neural field weighting, we find it is better for the ranker to score the whole document jointly, rather than generate a per-field score and aggregate. We find that different document fields may match different aspects of the query and therefore benefit from comparing with separate representations of the query text. The combination of techniques introduced here leads to a neural ranker that can take advantage of full document structure, including multiple instance and missing instance data, of variable length. The techniques significantly enhance the performance of the ranker, and also outperform a learning to rank baseline with hand-crafted features.