Inferring Concept Hierarchies from Text Corpora via Hyperbolic Embeddings
This work addresses the challenge of building concept hierarchies from text, which is important for natural language processing and knowledge representation, though it appears incremental as it builds on existing methods.
The paper tackles the problem of inferring is-a relationships from large text corpora by combining hyperbolic embeddings with Hearst patterns, achieving state-of-the-art performance on multiple benchmarks.
We consider the task of inferring is-a relationships from large text corpora. For this purpose, we propose a new method combining hyperbolic embeddings and Hearst patterns. This approach allows us to set appropriate constraints for inferring concept hierarchies from distributional contexts while also being able to predict missing is-a relationships and to correct wrong extractions. Moreover -- and in contrast with other methods -- the hierarchical nature of hyperbolic space allows us to learn highly efficient representations and to improve the taxonomic consistency of the inferred hierarchies. Experimentally, we show that our approach achieves state-of-the-art performance on several commonly-used benchmarks.