Adaptive Prototypical Networks with Label Words and Joint Representation Learning for Few-Shot Relation Classification

01/10/2021
by   Yan Xiao, et al.
8

Relation classification (RC) task is one of fundamental tasks of information extraction, aiming to detect the relation information between entity pairs in unstructured natural language text and generate structured data in the form of entity-relation triple. Although distant supervision methods can effectively alleviate the problem of lack of training data in supervised learning, they also introduce noise into the data, and still cannot fundamentally solve the long-tail distribution problem of the training instances. In order to enable the neural network to learn new knowledge through few instances like humans, this work focuses on few-shot relation classification (FSRC), where a classifier should generalize to new classes that have not been seen in the training set, given only a number of samples for each class. To make full use of the existing information and get a better feature representation for each instance, we propose to encode each class prototype in an adaptive way from two aspects. First, based on the prototypical networks, we propose an adaptive mixture mechanism to add label words to the representation of the class prototype, which, to the best of our knowledge, is the first attempt to integrate the label information into features of the support samples of each class so as to get more interactive class prototypes. Second, to more reasonably measure the distances between samples of each category, we introduce a loss function for joint representation learning to encode each support instance in an adaptive manner. Extensive experiments have been conducted on FewRel under different few-shot (FS) settings, and the results show that the proposed adaptive prototypical networks with label words and joint representation learning has not only achieved significant improvements in accuracy, but also increased the generalization ability of few-shot RC models.

READ FULL TEXT

page 1

page 6

research
04/15/2021

AdaPrompt: Adaptive Prompt-based Finetuning for Relation Extraction

In this paper, we reformulate the relation extraction task as mask langu...
research
10/15/2022

A Novel Few-Shot Relation Extraction Pipeline Based on Adaptive Prototype Fusion

Few-shot relation extraction (FSRE) aims at recognizing unseen relations...
research
05/27/2019

Combating Label Noise in Deep Learning Using Abstention

We introduce a novel method to combat label noise when training deep neu...
research
09/07/2022

Not All Instances Contribute Equally: Instance-adaptive Class Representation Learning for Few-Shot Visual Recognition

Few-shot visual recognition refers to recognize novel visual concepts fr...
research
11/24/2020

Persistent Mixture Model Networks for Few-Shot Image Classification

We introduce Persistent Mixture Model (PMM) networks for representation ...
research
07/19/2021

Self-Promoted Prototype Refinement for Few-Shot Class-Incremental Learning

Few-shot class-incremental learning is to recognize the new classes give...
research
04/26/2022

Function-words Enhanced Attention Networks for Few-Shot Inverse Relation Classification

The relation classification is to identify semantic relations between tw...

Please sign up or login with your details

Forgot password? Click here to reset