UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective

Yang Ping, JunYu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Pingjian Zhang, Jiaxing Zhang


Abstract
We propose a new paradigm for universal information extraction (IE) that is compatible with any schema format and applicable to a list of IE tasks, such as named entity recognition, relation extraction, event extraction and sentiment analysis. Our approach converts the text-based IE tasks as the token-pair problem, which uniformly disassembles all extraction targets into joint span detection, classification and association problems with a unified extractive framework, namely UniEX. UniEX can synchronously encode schema-based prompt and textual information, and collaboratively learn the generalized knowledge from pre-defined information using the auto-encoder language models. We develop a traffine attention mechanism to integrate heterogeneous factors including tasks, labels and inside tokens, and obtain the extraction target via a scoring matrix. Experiment results show that UniEX can outperform generative universal IE models in terms of performance and inference-speed on 14 benchmarks IE datasets with the supervised setting. The state-of-the-art performance in low-resource scenarios also verifies the transferability and effectiveness of UniEX.
Anthology ID:
2023.acl-long.907
Volume:
Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)
Month:
July
Year:
2023
Address:
Toronto, Canada
Editors:
Anna Rogers, Jordan Boyd-Graber, Naoaki Okazaki
Venue:
ACL
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
16424–16440
Language:
URL:
https://aclanthology.org/2023.acl-long.907
DOI:
10.18653/v1/2023.acl-long.907
Bibkey:
Cite (ACL):
Yang Ping, JunYu Lu, Ruyi Gan, Junjie Wang, Yuxiang Zhang, Pingjian Zhang, and Jiaxing Zhang. 2023. UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 16424–16440, Toronto, Canada. Association for Computational Linguistics.
Cite (Informal):
UniEX: An Effective and Efficient Framework for Unified Information Extraction via a Span-extractive Perspective (Ping et al., ACL 2023)
Copy Citation:
PDF:
https://aclanthology.org/2023.acl-long.907.pdf
Video:
 https://aclanthology.org/2023.acl-long.907.mp4