Non-Linear Multiple Field Interactions Neural Document Ranking
This research addresses the problem of improving document ranking for search engines and information retrieval systems by leveraging richer document structures beyond main body text and click data.
This paper explores the impact of query-field and non-linear field interactions on neural document ranking performance across two datasets. It analyzes how different architectural choices for neural models affect the utilization of multiple document fields.
Ranking tasks are usually based on the text of the main body of the page and the actions (clicks) of users on the page. There are other elements that could be leveraged to better contextualise the ranking experience (e.g. text in other fields, query made by the user, images, etc). We present one of the first in-depth analyses of field interaction for multiple field ranking in two separate datasets. While some works have taken advantage of full document structure, some aspects remain unexplored. In this work we build on previous analyses to show how query-field interactions, non-linear field interactions, and the architecture of the underlying neural model affect performance.