Fine-grained Entity Typing via Label Reasoning

Qing Liu, Hongyu Lin, Xinyan Xiao, Xianpei Han, Le Sun, Hua Wu


Abstract
Conventional entity typing approaches are based on independent classification paradigms, which make them difficult to recognize inter-dependent, long-tailed and fine-grained entity types. In this paper, we argue that the implicitly entailed extrinsic and intrinsic dependencies between labels can provide critical knowledge to tackle the above challenges. To this end, we propose Label Reasoning Network(LRN), which sequentially reasons fine-grained entity labels by discovering and exploiting label dependencies knowledge entailed in the data. Specifically, LRN utilizes an auto-regressive network to conduct deductive reasoning and a bipartite attribute graph to conduct inductive reasoning between labels, which can effectively model, learn and reason complex label dependencies in a sequence-to-set, end-to-end manner. Experiments show that LRN achieves the state-of-the-art performance on standard ultra fine-grained entity typing benchmarks, and can also resolve the long tail label problem effectively.
Anthology ID:
2021.emnlp-main.378
Volume:
Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
Month:
November
Year:
2021
Address:
Online and Punta Cana, Dominican Republic
Venue:
EMNLP
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
4611–4622
Language:
URL:
https://aclanthology.org/2021.emnlp-main.378
DOI:
10.18653/v1/2021.emnlp-main.378
Bibkey:
Cite (ACL):
Qing Liu, Hongyu Lin, Xinyan Xiao, Xianpei Han, Le Sun, and Hua Wu. 2021. Fine-grained Entity Typing via Label Reasoning. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 4611–4622, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Fine-grained Entity Typing via Label Reasoning (Liu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.378.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.378.mp4