Using Hyperbolic Geometry for FG-NET over Distantly Supervised data. (arXiv:2101.11212v2 [cs.CL] UPDATED)

Fine-Grained Named Entity Typing (\FGNET{}) classifies an entity mention into
a fine range of entity types. A large number of entity types make it difficult
to manually label the training data, thus distant supervision is used to
automatically acquire the training data. Distant supervision incurs a lot of
training noise which hinders the performance improvement of the FG-NET systems.
In this paper, we propose to use hyperbolic geometry for FG-NET with the hope
that it can help overcoming the noise …

arxiv data geometry