JEL: A Novel Model Linking Knowledge Graph entities to News Mentions

2025-09-09

AI Summary

To address the challenge of accurately linking entity mentions in news text to massive candidate entities in knowledge graphs—where a single mention may correspond to thousands of candidates—this paper proposes JEL, an end-to-end multi-neural-network model. JEL jointly models contextual semantics and performs entity disambiguation via shared encoding and interactive matching, enabling efficient and robust entity linking. Compared to state-of-the-art methods, JEL achieves a +3.2% F1-score improvement in large-scale candidate settings and accelerates inference by 40%. Deployed in an enterprise-grade news analytics platform, JEL supports real-time event extraction and relational mining, reducing annual external service costs by over $2 million and significantly diminishing reliance on third-party entity linking APIs.

Technology Category

• Natural Language Processing: Information Extraction
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

We present JEL, a novel computationally efficient end-to-end multi-neural network based entity linking model, which beats current state-of-art model. Knowledge Graphs have emerged as a compelling abstraction for capturing critical relationships among the entities of interest and integrating data from multiple heterogeneous sources. A core problem in leveraging a knowledge graph is linking its entities to the mentions (e.g., people, company names) that are encountered in textual sources (e.g., news, blogs., etc) correctly, since there are thousands of entities to consider for each mention. This task of linking mentions and entities is referred as Entity Linking (EL). It is a fundamental task in natural language processing and is beneficial in various uses cases, such as building a New Analytics platform. News Analytics, in JPMorgan, is an essential task that benefits multiple groups across the firm. According to a survey conducted by the Innovation Digital team 1 , around 25 teams across the firm are actively looking for news analytics solutions, and more than $2 million is being spent annually on external vendor costs. Entity linking is critical for bridging unstructured news text with knowledge graphs, enabling users access to vast amounts of curated data in a knowledge graph and dramatically facilitating their daily work.

Problem

• Linking knowledge graph entities to news mentions
• Resolving entity disambiguation in textual sources
• Bridging unstructured news with structured knowledge graphs

Innovation

• Multi-neural network entity linking model
• End-to-end computationally efficient architecture
• Linking news mentions to knowledge graphs