Publication Type
Journal Article
Version
acceptedVersion
Publication Date
2-2023
Abstract
Relation Extraction (RE) is a vital step to complete Knowledge Graph (KG) by extracting entity relations from texts. However, it usually suffers from the long-tail issue. The training data mainly concentrates on a few types of relations, leading to the lack of sufficient annotations for the remaining types of relations. In this paper, we propose a general approach to learn relation prototypes from unlabeled texts, to facilitate the long-tail relation extraction by transferring knowledge from the relation types with sufficient training data. We learn relation prototypes as an implicit factor between entities, which reflects the meanings of relations as well as their proximities for transfer learning. Specifically, we construct a co-occurrence graph from texts, and capture both first-order and second-order entity proximities for embedding learning. Based on this, we further optimize the distance from entity pairs to corresponding prototypes, which can be easily adapted to almost arbitrary RE frameworks. Thus, the learning of infrequent or even unseen relation types will benefit from semantically proximate relations through pairs of entities and large-scale textual information. We have conducted extensive experiments on two publicly available datasets: New York Times and Google Distant Supervision. Compared with eight state-of-the-art baselines, our proposed model achieves significant improvements (4.1% F1 on average). Further results on long-tail relations demonstrate the effectiveness of the learned relation prototypes. We further conduct an ablation study to investigate the impacts of varying components, and apply it to four basic relation extraction models to verify the generalization ability. Finally, we analyze several example cases to give intuitive impressions as qualitative analysis. Our codes will be released later.
Keywords
Annotations, Data mining, Knowledge Graph, long-tail, Prototype Learning, Prototypes, Relation Extraction, Training, Training data, Transfer learning, Urban areas
Discipline
Databases and Information Systems | Data Storage Systems
Research Areas
Data Science and Engineering
Publication
IEEE Transactions on Knowledge and Data Engineering
Volume
35
Issue
2
First Page
1761
Last Page
1774
ISSN
1041-4347
Identifier
10.1109/TKDE.2021.3096200
Publisher
Institute of Electrical and Electronics Engineers
Citation
CAO, Yixin; KUANG, Jun; GAO, Ming; ZHOU, Aoying; WEN, Yonggang; and CHUA, Tat-Seng.
Learning relation prototype from unlabeled texts for long-tail relation extraction. (2023). IEEE Transactions on Knowledge and Data Engineering. 35, (2), 1761-1774.
Available at: https://ink.library.smu.edu.sg/sis_research/7319
Copyright Owner and License
Authors
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1109/TKDE.2021.3096200