Event Extraction Service with Co-reference Resolution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for event extraction from documents and entity linking to private databases are inefficient, relying on manual review and rules-based automation, which are slow, expensive, and prone to errors, and struggle with scalability and accuracy, especially with large volumes of unstructured text.
Innovation Solution
An automated event extraction service using machine learning techniques for identifying triggers, entities, and semantic roles, and an entity linking service that disambiguates mentions in text against private databases using contextual representations and ETL tools, hosted in the cloud to provide scalable and accurate results.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If manual review and rules-based automation are used for event extraction, then implementation is straightforward, but processing speed and scalability are slow and limited
Solution Approach 1:
The patent replaces manual review and rules-based automation (mechanical systems) with machine learning models that automatically extract events, entities, and relationships from text. This substitution dramatically increases processing speed and scalability while reducing the need for manual configuration and maintenance of complex rule systems.
2Measurement precision
If machine learning techniques are used for event extraction, then accuracy and scalability improve, but computational resources and complexity increase
Solution Approach 1:
The patent segments the event extraction task into distinct components: trigger detection, entity recognition, and relationship extraction. Each component is handled by specialized machine learning models or modules, allowing for optimized processing of each subtask while maintaining overall system accuracy. This segmentation manages computational complexity by breaking down the complex extraction process into manageable, independent units.
3Loss of information
If entity linking to private databases is performed, then information completeness improves, but data security and access control challenges increase
Solution Approach 1:
The patent introduces an intermediary layer between the event extraction system and private databases. This intermediary manages entity linking while enforcing access control policies and security constraints. The intermediary resolves entity mentions in extracted events to canonical database records, ensuring information completeness while maintaining data security through controlled access mechanisms and audit trails.
Data Source
AI summary
Methods, systems, and computer-readable media for event extraction from documents with co-reference are disclosed. An event extraction service identifies one or more trigger groups in a document comprising text. An individual one of the trigger groups comprises one or more textual references to an occurrence of an event. The one or more trigger groups are associated with one or more semantic roles for entities. The event extraction service identifies one or more entity groups in the document. An individual one of the entity groups comprises one or more textual references to a real-world object. The event extraction service assigns one or more of the entity groups to one or more of the semantic roles. The event extraction service generates an output indicating the one or more trigger groups and one or more entity groups assigned to the semantic roles.