Finer Grained Entity Typing with TypeNet

Abstract

We consider the challenging problem of entity typing over an extremely fine grained set of types, wherein a single mention or entity can have many simultaneous and often hierarchically-structured types. Despite the importance of the problem, there is a relative lack of resources in the form of fine-grained, deep type hierarchies aligned to existing knowledge bases. In response, we introduce TypeNet, a dataset of entity types consisting of over 1941 types organized in a hierarchy, obtained by manually annotating a mapping from 1081 Freebase types to WordNet. We also experiment with several models comparable to state-of-the-art systems and explore techniques to incorporate a structure loss on the hierarchy with the standard mention typing loss, as a first step towards future research on this dataset.

Accepted at 6th Workshop on Automated Knowledge Base Construction (AKBC) at NIPS 2017

References in corpus (2)

• Adam: A Method for Stochastic Optimization
• Poincaré Embeddings for Learning Hierarchical Representations

Cited by in corpus (5)

• Low Resource Recognition and Linking of Biomedical Concepts from a Large Ontology
• Fine Grained Classification of Personal Data Entities
• A Neural Architecture for Person Ontology population
• Creating Training Sets via Weak Indirect Supervision
• EntEval: A Holistic Evaluation Benchmark for Entity Representations