Modeling Entity Type Interactions in Hyperbolic Space

An open Bachelor thesis, Contact a supervisor for more details!

Open Bachelor Thesis

Neural entity typing [1,2] aims at associating every entity mention in a context with multiple types. For example, an entity mention “Obama” in a sentence could be associated with multiple types “persons”, “politician”, “lawyer” and “author”. Usually, these types could be organized in a hierarchical structure, e.g., directed acyclic graphs (DAG).

Previous works embed types into a high-dimensional Euclidean [1] or hyperbolic space [2]. However, the prediction scores of these methods might be inconsistent with the inherent type hierarchy, e.g., an input mention must be labeled as "person" if it is already labeled as "politician" and "lawyer". In this work, we propose to associate each type with a hyperbolic region and model type-type relations as regional inclusions. The classification score is then modeled by the confidence of an instance being inside of the regions. The method would work on settings in which the type hierarchies are either explicitly given or unknown but can be derived from labeled data (e.g., by co-occurrence). We will evaluate the method in both settings. 

[1] Abhishek, A., Anand, A. and Awekar, A., 2017, February. Fine-grained entity type classification by jointly learning representations and label embeddings. In Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics (Vol. 1, pp. 797-807).
[2] López, F., Heinzerling, B. and Strube, M., 2019, August. Fine-Grained Entity Typing in Hyperbolic Space. In Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019) (pp. 169-180).



To the top of the page