Prompt-based Zero-shot Relation Classification with Semantic Knowledge Augmentation

12/08/2021
by   Jiaying Gong, et al.
0

Recognizing unseen relations with no training instances is a challenging task in the real world. In this paper, we propose a prompt-based model with semantic knowledge augmentation (ZS-SKA) to recognize unseen relations under the zero-shot setting. We generate augmented instances with unseen relations from instances with seen relations following a new word-level sentence translation rule. We design prompts based on an external knowledge graph to integrate semantic knowledge information learned from seen relations. Instead of using the actual label sets in the prompt template, we construct weighted virtual label words. By generating the representations of both seen and unseen relations with augmented instances and prompts through prototypical networks, distance is calculated to predict unseen relations. Extensive experiments conducted on three public datasets show that ZS-SKA outperforms state-of-the-art methods under the zero-shot scenarios. Our experimental results also demonstrate the effectiveness and robustness of ZS-SKA.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
10/30/2020

Logic-guided Semantic Representation Learning for Zero-Shot Relation Classification

Relation classification aims to extract semantic relations between entit...
research
11/15/2019

CNN-based Dual-Chain Models for Knowledge Graph Learning

Knowledge graph learning plays a critical role in integrating domain spe...
research
04/10/2021

ZS-BERT: Towards Zero-Shot Relation Extraction with Attribute Representation Learning

While relation extraction is an essential task in knowledge acquisition ...
research
03/29/2019

Integrating Semantic Knowledge to Tackle Zero-shot Text Classification

Insufficient or even unavailable training data of emerging classes is a ...
research
04/16/2022

A Hierarchical N-Gram Framework for Zero-Shot Link Prediction

Due to the incompleteness of knowledge graphs (KGs), zero-shot link pred...
research
05/31/2021

Pho(SC)Net: An Approach Towards Zero-shot Word Image Recognition in Historical Documents

Annotating words in a historical document image archive for word image r...
research
06/14/2023

Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation

Zero-Shot Learning (ZSL), which aims at automatically recognizing unseen...

Please sign up or login with your details

Forgot password? Click here to reset