Maximal Clique Based Non-Autoregressive Open Information Extraction

Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, Bin Wang


Abstract
Open Information Extraction (OpenIE) aims to discover textual facts from a given sentence. In essence, the facts contained in plain text are unordered. However, the popular OpenIE systems usually output facts sequentially in the way of predicting the next fact conditioned on the previous decoded ones, which enforce an unnecessary order on the facts and involve the error accumulation between autoregressive steps. To break this bottleneck, we propose MacroIE, a novel non-autoregressive framework for OpenIE. MacroIE firstly constructs a fact graph based on the table filling scheme, in which each node denotes a fact element, and an edge links two nodes that belong to the same fact. Then OpenIE can be reformulated as a non-parametric process of finding maximal cliques from the graph. It directly outputs the final set of facts in one go, thus getting rid of the burden of predicting fact order, as well as the error propagation between facts. Experiments conducted on two benchmark datasets show that our proposed model significantly outperforms current state-of-the-art methods, beats the previous systems by as much as 5.7 absolute gain in F1 score.
Anthology ID:
2021.emnlp-main.764
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:
9696–9706
Language:
URL:
https://aclanthology.org/2021.emnlp-main.764
DOI:
10.18653/v1/2021.emnlp-main.764
Bibkey:
Cite (ACL):
Bowen Yu, Yucheng Wang, Tingwen Liu, Hongsong Zhu, Limin Sun, and Bin Wang. 2021. Maximal Clique Based Non-Autoregressive Open Information Extraction. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 9696–9706, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.
Cite (Informal):
Maximal Clique Based Non-Autoregressive Open Information Extraction (Yu et al., EMNLP 2021)
Copy Citation:
PDF:
https://aclanthology.org/2021.emnlp-main.764.pdf
Video:
 https://aclanthology.org/2021.emnlp-main.764.mp4
Data
CaRB