Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem

Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, Hamed Firooz


Abstract
We propose an autoregressive entity linking model, that is trained with two auxiliary tasks, and learns to re-rank generated samples at inference time. Our proposed novelties address two weaknesses in the literature. First, a recent method proposes to learn mention detection and then entity candidate selection, but relies on predefined sets of candidates. We use encoder-decoder autoregressive entity linking in order to bypass this need, and propose to train mention detection as an auxiliary task instead. Second, previous work suggests that re-ranking could help correct prediction errors. We add a new, auxiliary task, match prediction, to learn re-ranking. Without the use of a knowledge base or candidate sets, our model sets a new state of the art in two benchmark datasets of entity linking: COMETA in the biomedical domain, and AIDA-CoNLL in the news domain. We show through ablation studies that each of the two auxiliary tasks increases performance, and that re-ranking is an important factor to the increase. Finally, our low-resource experimental results suggest that performance on the main task benefits from the knowledge learned by the auxiliary tasks, and not just from the additional training data.
Anthology ID:
2022.findings-acl.156
Volume:
Findings of the Association for Computational Linguistics: ACL 2022
Month:
May
Year:
2022
Address:
Dublin, Ireland
Editors:
Smaranda Muresan, Preslav Nakov, Aline Villavicencio
Venue:
Findings
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
1972–1983
Language:
URL:
https://aclanthology.org/2022.findings-acl.156
DOI:
10.18653/v1/2022.findings-acl.156
Bibkey:
Cite (ACL):
Khalil Mrini, Shaoliang Nie, Jiatao Gu, Sinong Wang, Maziar Sanjabi, and Hamed Firooz. 2022. Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1972–1983, Dublin, Ireland. Association for Computational Linguistics.
Cite (Informal):
Detection, Disambiguation, Re-ranking: Autoregressive Entity Linking as a Multi-Task Problem (Mrini et al., Findings 2022)
Copy Citation:
PDF:
https://aclanthology.org/2022.findings-acl.156.pdf
Video:
 https://aclanthology.org/2022.findings-acl.156.mp4
Data
AIDA CoNLL-YAGOCOMETA