Word-Entity Duet Representations for Document Ranking
This work addresses the problem of noisy entity representations in knowledge-based retrieval for search engines, offering an incremental improvement through attention mechanisms.
The paper tackles ad-hoc document retrieval by proposing a word-entity duet framework that integrates word-based and entity-based representations with knowledge graphs, resulting in significant performance improvements over baseline systems on the TREC Web Track.
This paper presents a word-entity duet framework for utilizing knowledge bases in ad-hoc retrieval. In this work, the query and documents are modeled by word-based representations and entity-based representations. Ranking features are generated by the interactions between the two representations, incorporating information from the word space, the entity space, and the cross-space connections through the knowledge graph. To handle the uncertainties from the automatically constructed entity representations, an attention-based ranking model AttR-Duet is developed. With back-propagation from ranking labels, the model learns simultaneously how to demote noisy entities and how to rank documents with the word-entity duet. Evaluation results on TREC Web Track ad-hoc task demonstrate that all of the four-way interactions in the duet are useful, the attention mechanism successfully steers the model away from noisy entities, and together they significantly outperform both word-based and entity-based learning to rank systems.