Fine-Grained Entity Typing with High-Multiplicity Assignments
This addresses the challenge of handling rich, semi-open type systems in entity typing for applications like knowledge base construction, though it appears incremental as it builds on existing fine-grained typing work.
The paper tackled the problem of fine-grained entity typing in the high-multiplicity regime, where entities have many types, and introduced a set-prediction approach that outperformed unstructured baselines on a new Wikipedia-based corpus.
As entity type systems become richer and more fine-grained, we expect the number of types assigned to a given entity to increase. However, most fine-grained typing work has focused on datasets that exhibit a low degree of type multiplicity. In this paper, we consider the high-multiplicity regime inherent in data sources such as Wikipedia that have semi-open type systems. We introduce a set-prediction approach to this problem and show that our model outperforms unstructured baselines on a new Wikipedia-based fine-grained typing corpus.