Towards One-Shot Learning for Text Classification using Inductive Logic Programming

Ghazal Afroozi Milani; Daniel Cyrus; Alireza Tamaddoni-Nezhad

doi:10.48550/arxiv.2308.15885

Back

Preprint

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

Ghazal Afroozi Milani, Daniel Cyrus and Alireza Tamaddoni-Nezhad

arXiv.org

30/08/2023

DOI: https://doi.org/10.48550/arxiv.2308.15885

Abstract

Computer Science - Computation and Language

Computer Science - Learning

Computer Science - Logic in Computer Science

EPTCS 385, 2023, pp. 69-79 With the ever-increasing potential of AI to perform personalised tasks, it is becoming essential to develop new machine learning techniques which are data-efficient and do not require hundreds or thousands of training data. In this paper, we explore an Inductive Logic Programming approach for one-shot text classification. In particular, we explore the framework of Meta-Interpretive Learning (MIL), along with using common-sense background knowledge extracted from ConceptNet. Results indicate that MIL can learn text classification rules from a small number of training examples. Moreover, the higher complexity of chosen examples, the higher accuracy of the outcome.

Metrics

Details

Title: Towards One-Shot Learning for Text Classification using Inductive Logic Programming
Creators: Ghazal Afroozi Milani - University of Surrey
Daniel Cyrus - University of Surrey
Alireza Tamaddoni-Nezhad - University of Surrey
Publication Details: arXiv.org
Identifiers: 99941845202346
Academic Unit: School of Computer Science and Electronic Engineering
Language: English
Resource Type: Preprint

Towards One-Shot Learning for Text Classification using Inductive Logic Programming

Abstract

Metrics

Details

Usage Policy