Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing

Vera Provatorova, Samarth Bhargav, Svitlana Vakulenko, Evangelos Kanoulas


Abstract
Entity disambiguation (ED) is the last step of entity linking (EL), when candidate entities are reranked according to the context they appear in. All datasets for training and evaluating models for EL consist of convenience samples, such as news articles and tweets, that propagate the prior probability bias of the entity distribution towards more frequently occurring entities. It was shown that the performance of the EL systems on such datasets is overestimated since it is possible to obtain higher accuracy scores by merely learning the prior. To provide a more adequate evaluation benchmark, we introduce the ShadowLink dataset, which includes 16K short text snippets annotated with entity mentions. We evaluate and report the performance of popular EL systems on the ShadowLink benchmark. The results show a considerable difference in accuracy between more and less common entities for all of the EL systems under evaluation, demonstrating the effect of prior probability bias and entity overshadowing.
Anthology ID:
2021.emnlp-main.820
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Editors:
Marie-Francine Moens, Xuanjing Huang, Lucia Specia, Scott Wen-tau Yih
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
10501–10510
Language:
URL:
https://aclanthology.org/2021.emnlp-main.820
DOI:
10.18653/v1/2021.emnlp-main.820
Bibkey:
Cite (ACL):
Vera Provatorova, Samarth Bhargav, Svitlana Vakulenko, and Evangelos Kanoulas. 2021. Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 10501–10510, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Robustness Evaluation of Entity Disambiguation Using Prior Probes: the Case of Entity Overshadowing (Provatorova et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.820.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.820.mp4