Entity Concept-enhanced Few-shot Relation Extraction

Abstract

Few-shot relation extraction (FSRE) is of great importance in long-tail distribution problem, especially in special domain with low-resource data. Most existing FSRE algorithms fail to accurately classify the relations merely based on the information of the sentences together with the recognized entity pairs, due to limited samples and lack of knowledge. To address this problem, in this paper, we proposed a novel entity CONCEPT-enhanced FEw-shot Relation Extraction scheme (ConceptFERE), which introduces the inherent concepts of entities to provide clues for relation prediction and boost the relations classification performance. Firstly, a concept-sentence attention module is developed to select the most appropriate concept from multiple concepts of each entity by calculating the semantic similarity between sentences and concepts. Secondly, a self-attention based fusion module is presented to bridge the gap of concept embedding and sentence embedding from different semantic spaces. Extensive experiments on the FSRE benchmark dataset FewRel have demonstrated the effectiveness and the superiority of the proposed ConceptFERE scheme as compared to the state-of-the-art baselines. Code is available at https://github.com/LittleGuoKe/ConceptFERE.

arXiv commentAccepted at ACL2021

References in corpus (7)

• Prototypical Networks for Few-shot Learning
• Few-Shot Learning with Graph Neural Networks
• Few-shot Relation Extraction via Bayesian Meta-learning on Relation Graphs
• FewRel: A Large-Scale Supervised Few-Shot Relation Classification Dataset with State-of-the-Art Evaluation
• More Data, More Relations, More Context and More Openness: A Review and Outlook for Relation Extraction
• Beyond Word Embeddings: Learning Entity and Concept Representations from Large Scale Knowledge Bases
• Long-tail Relation Extraction via Knowledge Graph Embeddings and Graph Convolution Networks