Entities as Experts: Sparse Memory Access with Entity Supervision

Thibault Févry, Livio Baldini Soares, Nicholas FitzGerald, Eunsol Choi, Tom Kwiatkowski


Abstract
We focus on the problem of capturing declarative knowledge about entities in the learned parameters of a language model. We introduce a new model—Entities as Experts (EaE)—that can access distinct memories of the entities mentioned in a piece of text. Unlike previous efforts to integrate entity knowledge into sequence models, EaE’s entity representations are learned directly from text. We show that EaE’s learned representations capture sufficient knowledge to answer TriviaQA questions such as “Which Dr. Who villain has been played by Roger Delgado, Anthony Ainley, Eric Roberts?”, outperforming an encoder-generator Transformer model with 10x the parameters on this task. According to the Lama knowledge probes, EaE contains more factual knowledge than a similar sized Bert, as well as previous approaches that integrate external sources of entity knowledge. Because EaE associates parameters with specific entities, it only needs to access a fraction of its parameters at inference time, and we show that the correct identification and representation of entities is essential to EaE’s performance.
Anthology ID:
2020.emnlp-main.400
Volume:
Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)
Month:
November
Year:
2020
Address:
Online
Editors:
Bonnie Webber, Trevor Cohn, Yulan He, Yang Liu
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4937–4951
Language:
URL:
https://aclanthology.org/2020.emnlp-main.400
DOI:
10.18653/v1/2020.emnlp-main.400
Bibkey:
Cite (ACL):
Thibault Févry, Livio Baldini Soares, Nicholas FitzGerald, Eunsol Choi, and Tom Kwiatkowski. 2020. Entities as Experts: Sparse Memory Access with Entity Supervision. In Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pages 4937–4951, Online. Association for Computational Linguistics.
Cite (Informal):
Entities as Experts: Sparse Memory Access with Entity Supervision (Févry et al., EMNLP 2020)
Copy Citation:
PDF:
https://preview.aclanthology.org/naacl24-info/2020.emnlp-main.400.pdf
Video:
 https://slideslive.com/38938928
Data
LAMATriviaQAWebQuestions