Microsoft technology licensing, llc (20240311656). Scalable and Resource-Efficient Knowledge-Graph Completion simplified abstract
Scalable and Resource-Efficient Knowledge-Graph Completion
Organization Name
microsoft technology licensing, llc
Inventor(s)
Xiaodong Liu of Woodinville WA (US)
Sanxing Chen of Durham NC (US)
Jianfeng Gao of Woodinville WA (US)
Scalable and Resource-Efficient Knowledge-Graph Completion - A simplified explanation of the abstract
This abstract first appeared for US patent application 20240311656 titled 'Scalable and Resource-Efficient Knowledge-Graph Completion
- Simplified Explanation:**
The technique described in the patent application efficiently completes knowledge graphs by predicting target entities based on source entity information and relations.
- Key Features and Innovation:**
- Scalable and resource-efficient technique for knowledge graph completion
- Utilizes machine-trained encoder model to map source entity data to encoded information
- Predicts target entity based on encoded information and relations
- Considers neighboring entities and their relations for prediction
- Allows transfer of knowledge across training stages
- Potential Applications:**
This technology can be applied in various fields such as natural language processing, information retrieval, and data mining for improving knowledge graph completion and entity prediction tasks.
- Problems Solved:**
This technology addresses the challenges of completing knowledge graphs efficiently and accurately by leveraging machine learning models and encoded information from source entities.
- Benefits:**
- Improved accuracy in predicting target entities in knowledge graphs
- Enhanced scalability and resource efficiency in knowledge graph completion tasks
- Facilitates transfer of knowledge across training stages for continuous learning and improvement
- Commercial Applications:**
Potential commercial applications include enhancing search engines, recommendation systems, and information retrieval systems by improving entity prediction and knowledge graph completion processes.
- Prior Art:**
Researchers can explore prior art related to machine learning models for knowledge graph completion, entity prediction, and natural language processing tasks to understand the evolution of similar technologies.
- Frequently Updated Research:**
Stay updated on advancements in machine learning models, natural language processing techniques, and knowledge graph completion methods to enhance the performance and efficiency of this technology.
- Questions about Knowledge Graph Completion:**
1. How does this technique improve the efficiency of knowledge graph completion tasks? 2. What are the key factors considered in predicting target entities based on source entity information and relations?
Original Abstract Submitted
a technique performs the task of knowledge-graph completion in a manner that is both scalable and resource efficient. in some implementations, the technique identifies a source entity having a source-target relation that connects the source entity to a yet-to-be-determined target entity. the technique also identifies a source-entity data item that provides a passage of source-entity text pertaining to the source entity. the technique uses a machine-trained encoder model to map the source-entity data item to source-entity encoded information. the technique then predicts an identity of the target entity based on the source-entity encoded information, and based on predicate encoded information that encodes the source-target relation. in some implementations, the technique also predicts the target entity based on a consideration of one or more neighboring entities that are connected to the source entity and their respective source-to-neighbor relations. the technique further allows transfer of knowledge across knowledge-graph training stages.