Finer Grained Entity Typing with TypeNet
This addresses the lack of resources for fine-grained entity typing, which is incremental as it builds on existing knowledge bases.
The authors tackled the problem of entity typing with an extremely fine-grained set of types by introducing TypeNet, a dataset of over 1941 types organized in a hierarchy, and experimented with models to incorporate structure loss.
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.