Modeling Fine-Grained Entity Types with Box Embeddings

Understand

Neural entity typing models typically represent fine-grained entity types as vectors in a high-dimensional space, but such spaces are not well-suited to modeling these types' complex interdependencies.

• We study the ability of box embeddings, which embed concepts as d-dimensional hyperrectangles, to capture hierarchies of types even when these relationships are not defined explicitly in the ontology.
• Our model represents both types and entity mentions as boxes.
• Each mention and its context are fed into a BERT-based model to embed that mention in our box space; essentially, this model leverages typological clues present in the surface text to hypothesize a type representation for the mention.