Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enabling Roll-up and Drill-down Operations in News Exploration with Knowledge Graphs for Due Diligence and Risk Management

Sha Wang, Yuchen Li, Hanhua Xiao, Zhifeng Bao, Lambert Deng, Yanfei Dong

TL;DR

NCExplorer addresses the manual, keyword-driven nature of financial news due diligence by introducing an OLAP-inspired framework that links news articles to external Knowledge Graphs for semantic roll-up and drill-down. It combines ontology-based and instance-based knowledge via a novel relevance framework, including ontology relevance, context relevance, and a connectivity-based score, plus a subtopic scoring function with coverage, specificity, and diversity. A scalable, unbiased random-walk connectivity estimator enables efficient computation over large KGs, and extensive crowd-sourced evaluations show NCExplorer outperforms state-of-the-art methods across topics, with GPT-based re-ranking offering additional gains. The approach delivers improved discovery, explainability, and productivity for risk management tasks, and the authors release datasets, code, and results to support adoption and further research.

Abstract

Efficient news exploration is crucial in real-world applications, particularly within the financial sector, where numerous control and risk assessment tasks rely on the analysis of public news reports. The current processes in this domain predominantly rely on manual efforts, often involving keywordbased searches and the compilation of extensive keyword lists. In this paper, we introduce NCEXPLORER, a framework designed with OLAP-like operations to enhance the news exploration experience. NCEXPLORER empowers users to use roll-up operations for a broader content overview and drill-down operations for detailed insights. These operations are achieved through integration with external knowledge graphs (KGs), encompassing both fact-based and ontology-based structures. This integration significantly augments exploration capabilities, offering a more comprehensive and efficient approach to unveiling the underlying structures and nuances embedded in news content. Extensive empirical studies through master-qualified evaluators on Amazon Mechanical Turk demonstrate NCEXPLORER's superiority over existing state-of-the-art news search methodologies across an array of topic domains, using real-world news datasets.

Enabling Roll-up and Drill-down Operations in News Exploration with Knowledge Graphs for Due Diligence and Risk Management

TL;DR

NCExplorer addresses the manual, keyword-driven nature of financial news due diligence by introducing an OLAP-inspired framework that links news articles to external Knowledge Graphs for semantic roll-up and drill-down. It combines ontology-based and instance-based knowledge via a novel relevance framework, including ontology relevance, context relevance, and a connectivity-based score, plus a subtopic scoring function with coverage, specificity, and diversity. A scalable, unbiased random-walk connectivity estimator enables efficient computation over large KGs, and extensive crowd-sourced evaluations show NCExplorer outperforms state-of-the-art methods across topics, with GPT-based re-ranking offering additional gains. The approach delivers improved discovery, explainability, and productivity for risk management tasks, and the authors release datasets, code, and results to support adoption and further research.

Abstract

Efficient news exploration is crucial in real-world applications, particularly within the financial sector, where numerous control and risk assessment tasks rely on the analysis of public news reports. The current processes in this domain predominantly rely on manual efforts, often involving keywordbased searches and the compilation of extensive keyword lists. In this paper, we introduce NCEXPLORER, a framework designed with OLAP-like operations to enhance the news exploration experience. NCEXPLORER empowers users to use roll-up operations for a broader content overview and drill-down operations for detailed insights. These operations are achieved through integration with external knowledge graphs (KGs), encompassing both fact-based and ontology-based structures. This integration significantly augments exploration capabilities, offering a more comprehensive and efficient approach to unveiling the underlying structures and nuances embedded in news content. Extensive empirical studies through master-qualified evaluators on Amazon Mechanical Turk demonstrate NCEXPLORER's superiority over existing state-of-the-art news search methodologies across an array of topic domains, using real-world news datasets.
Paper Structure (20 sections, 7 equations, 8 figures, 3 tables)

This paper contains 20 sections, 7 equations, 8 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Related Work
  3. NCExplorer
  4. Roll-up Operation.
  5. Ontology Relevance
  6. Context Relevance
  7. Drill-down Operation.
  8. Coverage
  9. Specificity
  10. Diversity
  11. Connectivity Score Estimation
  12. Evaluation
  13. Roll-up Operation
  14. Concept Document Rank Evaluation
  15. Efficiency Study
  16. ...and 5 more sections

Figures (8)

  • Figure 1: NCExplorerroll-up and drill-down example. A user can roll-up a specific entity "FTX" to an abstract topic"Bitcoin Exchange" and drill-down to other topics in the result like "Regulator". Yellow boxes indicate user operations and green boxes show results.
  • Figure 2: KG Concept and Instance Spaces
  • Figure 3: NCExplorer Architecture.
  • Figure 4: Performance Study: indexing time
  • Figure 5: Performance Study: retrieval time
  • ...and 3 more figures

Theorems & Definitions (2)

  • Definition 1
  • Definition 2