Building a Knowledge Graph from Natural Language Definitions for Interpretable Text Entailment Recognition
This work addresses the need for interpretable knowledge bases in NLP, offering a domain-specific tool for text entailment recognition.
The authors tackled the problem of structuring natural language definitions into a knowledge graph to improve interpretability in semantic tasks, resulting in WordNetGraph, which was successfully applied to provide clear justifications for text entailment decisions.
Natural language definitions of terms can serve as a rich source of knowledge, but structuring them into a comprehensible semantic model is essential to enable them to be used in semantic interpretation tasks. We propose a method and provide a set of tools for automatically building a graph world knowledge base from natural language definitions. Adopting a conceptual model composed of a set of semantic roles for dictionary definitions, we trained a classifier for automatically labeling definitions, preparing the data to be later converted to a graph representation. WordNetGraph, a knowledge graph built out of noun and verb WordNet definitions according to this methodology, was successfully used in an interpretable text entailment recognition approach which uses paths in this graph to provide clear justifications for entailment decisions.