# Neural Document Expansion with User Feedback

## TL;DR

This paper introduces NeuDEF, a neural document expansion method that leverages user click feedback to improve neural ranking accuracy, demonstrating significant performance gains on commercial search logs.

## Contribution

NeuDEF is a novel neural document expansion approach that uses click-based expansion terms with learned attention, integrated end-to-end into neural rankers.

## Key findings

- NeuDEF significantly improves neural ranking accuracy.
- Click query contributions enhance expansion effectiveness.
- Document popularity influences NeuDEF's performance.

## Abstract

This paper presents a neural document expansion approach (NeuDEF) that enriches document representations for neural ranking models. NeuDEF harvests expansion terms from queries which lead to clicks on the document and weights these expansion terms with learned attention. It is plugged into a standard neural ranker and learned end-to-end. Experiments on a commercial search log demonstrate that NeuDEF significantly improves the accuracy of state-of-the-art neural rankers and expansion methods on queries with different frequencies. Further studies show the contribution of click queries and learned expansion weights, as well as the influence of document popularity of NeuDEF's effectiveness.