DBpedia triple filtering improves data precision for language generation
Validating DBpedia Triple Sets for Natural Language Generation
Computation and Language
Summary
When computers create sentences from data, the quality of that data matters a lot. This study looks closely at DBpedia, a big collection of facts, and finds ways to spot and remove unclear or wrong bits. The authors show their method picks correct facts with very high accuracy and can find many more right facts without adding mistakes. This helps make the sentences computers write based on this data clearer and more reliable.
What this means in practice
- •For natural language generation developers: Improve the quality of data inputs by filtering DBpedia triples to generate more accurate natural language outputs.
- •For knowledge base engineers: Enhance DBpedia property definitions to recover more correct triples while maintaining filtering precision for better data reliability.
Authors
Mark Andrade, Simon Mille, Anya Belz, Brian Davis
Abstract
We present a study of the quality of individual DBpedia triples from the perspective of Natural Language Generation, and propose and evaluate an approach for collecting entity-specific triple sets that filters out questionable triples while minimizing the loss of correct ones. We show in an evaluation against manually annotated data that with validation rules, it is possible to reach 98% precision in triple selection, and with improvements to a few Property definitions, it is possible to improve recall by 40% without harming precision.