Fine-Grained Entity Typing in Hyperbolic Space
This work addresses entity typing for NLP researchers, but it is incremental as it shows mixed results and depends on specific conditions.
The paper tackled the problem of representing hierarchical information in large type inventories for entity typing by evaluating hyperbolic embeddings against Euclidean ones, finding that hyperbolic models improve performance in some cases depending on inventory granularity and relation inference methods.
How can we represent hierarchical information present in large type inventories for entity typing? We study the ability of hyperbolic embeddings to capture hierarchical relations between mentions in context and their target types in a shared vector space. We evaluate on two datasets and investigate two different techniques for creating a large hierarchical entity type inventory: from an expert-generated ontology and by automatically mining type co-occurrences. We find that the hyperbolic model yields improvements over its Euclidean counterpart in some, but not all cases. Our analysis suggests that the adequacy of this geometry depends on the granularity of the type inventory and the way hierarchical relations are inferred.