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

TL;DR

This paper investigates using Meta-Interpretive Learning with common-sense knowledge for one-shot text classification, demonstrating that it can learn effective rules from minimal data and that more complex examples improve accuracy.

Contribution

It introduces a novel approach combining MIL and ConceptNet for data-efficient one-shot text classification, advancing the use of logic programming in NLP.

Findings

MIL can learn classification rules from few examples

Higher complexity examples lead to better accuracy

Incorporating common-sense knowledge improves results

Abstract

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.