A Simple yet Effective Relation Information Guided Approach for Few-Shot Relation Extraction

Abstract

Few-Shot Relation Extraction aims at predicting the relation for a pair of entities in a sentence by training with a few labelled examples in each relation. Some recent works have introduced relation information (i.e., relation labels or descriptions) to assist model learning based on Prototype Network. However, most of them constrain the prototypes of each relation class implicitly with relation information, generally through designing complex network structures, like generating hybrid features, combining with contrastive learning or attention networks. We argue that relation information can be introduced more explicitly and effectively into the model. Thus, this paper proposes a direct addition approach to introduce relation information. Specifically, for each relation class, the relation representation is first generated by concatenating two views of relations (i.e., [CLS] token embedding and the mean value of embeddings of all tokens) and then directly added to the original prototype for both train and prediction. Experimental results on the benchmark dataset FewRel 1.0 show significant improvements and achieve comparable results to the state-of-theart, which demonstrates the effectiveness of our proposed approach. Besides, further analyses verify that the direct addition is a much more effective way to integrate the relation representations and the original prototypes. 1 2

DiffFSRE: Diffusion-Enhanced Prototypical Network for Few-Shot Relation Extraction

“…This approach optimized the measurement between sentences and abstracted the core characteristics of relation classes by inferring prototypes, thereby further enhancing the performance of relation extraction. Liu et al [29] introduced a straightforward yet powerful approach incorporating relation information into the prototypical network. The fundamental concept involves incorporating relation representations through a direct addition operation rather than designing intricate structures.…”

Multi-Head Self-Attention-Enhanced Prototype Network with Contrastive–Center Loss for Few-Shot Relation Extraction

“…( 9) DAPL [53]: Utilizes the shortest dependency path information between entities in the prototype network. (10) SimpleF-SRE [18]: Concatenates the two representations of relational information and directly incorporates them into the prototype representation. ( 11) CP [48]: Utilizes the entity-masking contrast pre-training framework by randomly masking entity references.…”

“…HCRP [17] employs relation-prototype contrastive learning to better leverage relationship information and obtain diverse and discriminative prototype representations. SimpleFSRE [18] improves model performance by concatenating two representations of relationship information and directly incorporating them into the prototype representation. PRM [19] combines a gating mechanism to utilize relationship description information, determining the degree of preservation and an update of both the prototype and relationship information.…”

Chain of Thought with Explicit Evidence Reasoning for Few-shot Relation Extraction

“…Many approaches (Qu et al, 2020; incorporate external knowledge to improve performance given the scarcity of training data. Another line of FSRE research (Gao et al, 2019a;Liu et al, 2022b) relies solely on the input text and provided relation description information, without incorporating external knowledge. Most of the previous methods usually adopt complicated designs of neural networks or introduce external knowledge, which can be labor-intensive in realistic scenarios.…”