Mixing Context Granularities for Improved Entity Linking on Question Answering Data across Entity Categories

TL;DR

This paper introduces a neural model that improves entity linking in question answering by modeling context at multiple granularities, achieving significant performance gains across entity types.

Contribution

The paper proposes a jointly optimized neural architecture for entity mention detection and disambiguation that leverages multi-granularity context modeling, outperforming previous methods.

Findings

Achieved an 8% average improvement over state-of-the-art.

Demonstrated strong performance across various entity categories.

Created new benchmarks using Wikidata and QA datasets.

Abstract

The first stage of every knowledge base question answering approach is to link entities in the input question. We investigate entity linking in the context of a question answering task and present a jointly optimized neural architecture for entity mention detection and entity disambiguation that models the surrounding context on different levels of granularity. We use the Wikidata knowledge base and available question answering datasets to create benchmarks for entity linking on question answering data. Our approach outperforms the previous state-of-the-art system on this data, resulting in an average 8% improvement of the final score. We further demonstrate that our model delivers a strong performance across different entity categories.