AKEM: Aligning Knowledge Base to Queries with Ensemble Model for Entity Recognition and Linking

TL;DR

This paper introduces AKEM, an ensemble model that improves entity recognition and linking in short queries by expanding the knowledge base, using external knowledge, and applying machine learning and rule-based filtering, achieving an F1 score of 0.535.

Contribution

The paper proposes a novel ensemble approach combining knowledge base expansion, external knowledge, machine learning, and rule-based filtering for entity recognition and linking.

Findings

Achieved an F1 score of 0.535 on the task.

Improved recall through knowledge base expansion and external knowledge.

Enhanced precision with rule-based filtering.

Abstract

This paper presents a novel approach to address the Entity Recognition and Linking Challenge at NLPCC 2015. The task involves extracting named entity mentions from short search queries and linking them to entities within a reference Chinese knowledge base. To tackle this problem, we first expand the existing knowledge base and utilize external knowledge to identify candidate entities, thereby improving the recall rate. Next, we extract features from the candidate entities and utilize Support Vector Regression and Multiple Additive Regression Tree as scoring functions to filter the results. Additionally, we apply rules to further refine the results and enhance precision. Our method is computationally efficient and achieves an F1 score of 0.535.