Modeling Fine-Grained Entity Types with Box Embeddings

Yasumasa Onoe, Michael Boratko, Andrew McCallum, Greg Durrett


Abstract
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. Box containment can then be used to derive both the posterior probability of a mention exhibiting a given type and the conditional probability relations between types themselves. We compare our approach with a vector-based typing model and observe state-of-the-art performance on several entity typing benchmarks. In addition to competitive typing performance, our box-based model shows better performance in prediction consistency (predicting a supertype and a subtype together) and confidence (i.e., calibration), demonstrating that the box-based model captures the latent type hierarchies better than the vector-based model does.
Anthology ID:
2021.acl-long.160
Volume:
Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)
Month:
August
Year:
2021
Address:
Online
Editors:
Chengqing Zong, Fei Xia, Wenjie Li, Roberto Navigli
Venues:
ACL | IJCNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
2051–2064
Language:
URL:
https://aclanthology.org/2021.acl-long.160
DOI:
10.18653/v1/2021.acl-long.160
Bibkey:
Cite (ACL):
Yasumasa Onoe, Michael Boratko, Andrew McCallum, and Greg Durrett. 2021. Modeling Fine-Grained Entity Types with Box Embeddings. In Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pages 2051–2064, Online. Association for Computational Linguistics.
Cite (Informal):
Modeling Fine-Grained Entity Types with Box Embeddings (Onoe et al., ACL-IJCNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.acl-long.160.pdf
Video:
 https://aclanthology.org/2021.acl-long.160.mp4
Code
 yasumasaonoe/Box4Types
Data
FIGEROpen Entity