A Prototype Network Enhanced Relation Semantic Representation for Few-shot Relation Extraction
Open Access
- 2 December 2022
- journal article
- research article
- Published by Springer Nature in Human-Centric Intelligent Systems
- Vol. 3 (1) , 1-12
Abstract
Few-shot relation extraction is one of the current research focuses. The key to this research is to fully extract the relation semantic information through very little training data. Intuitively, raising the relation semantics awareness in sentences can improve the efficiency of the model to extract relation features to alleviate the overfitting problem in few-shot learning. Therefore, we propose an enhanced relation semantic feature model based on prototype network to extract relations from few-shot texts. Firstly, we design a multi-level embedding encoder with position information and Transformer, which uses local information in the text to enhance the relation semantics representation. Secondly, the encoded relation features are fed into the novel prototype network, which designs a method that utilizes query prototype-level attention to guide the extraction of supporting prototypes, thereby enhancing the prototypes representation to better classify the relations in query sentences. Finally, through experimental comparison and discussion, we prove and analyze the effectiveness of the proposed multi-level embedding encoder, and prototype-level attention can enhance the stability of the model. Furthermore, our model has substantial improvements over baseline methods.Keywords
Funding Information
- the Science and Technology Project of Hebei Education Department under Grant (Nos.QN2021145)
- Youth and Middle-aged Scientific and Technological Innovation Leading Talents Program of the Corps (No.204200510002)
This publication has 26 references indexed in Scilit:
- Chemical disease relation extraction task using genetic algorithm with two novelvoting methods for classifier subset selectionTurkish Journal of Electrical Engineering and Computer Sciences, 2020
- Structural block driven enhanced convolutional neural representation for relation extractionApplied Soft Computing, 2020
- Large Margin Prototypical Network for Few-shot Relation Classification with Fine-grained Features2019
- Hybrid Attention-Based Prototypical Networks for Noisy Few-Shot Relation ClassificationProceedings of the AAAI Conference on Artificial Intelligence, 2019
- FewRel 2.0: Towards More Challenging Few-Shot Relation Classification2019
- Multi-Level Matching and Aggregation Network for Few-Shot Relation Classification2019
- Multiple order semantic relation extractionNeural Computing and Applications, 2018
- FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation2018
- Neural Relation Extraction with Selective Attention over Instances2016
- Distant supervision for relation extraction without labeled data2009