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

Ghazal Afroozi Milani, Daniel Cyrus, Alireza Tamaddoni-Nezhad
8/30/2023
cs.LGcs.CLcs.LO

No official code found. Best implementation: ghazalmilani/One-Shot-Learning-from-Text-ICLP2023 (0 stars, last commit 2025-01-17).

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.

View on arXivView PDF

Code Implementations(1)

ghazalmilani/One-Shot-Learning-from-Text-ICLP2023Community100%
00Prolog, Jupyter NotebookJun 23, 20231 years ago

Similar Papers

Improve Meta-learning for Few-Shot Text Classification with All You Can Acquire from the Tasks

84% match1 repo72024

ContrastNet: A Contrastive Learning Framework for Few-Shot Text Classification

83% match1 repo252023

Auxiliary Descriptive Knowledge for Few-Shot Adaptation of Vision-Language Model

83% match2025

WC-SBERT: Zero-Shot Text Classification via SBERT with Self-Training for Wikipedia Categories

83% match1 repo32023

Boosting Prompt-Based Self-Training With Mapping-Free Automatic Verbalizer for Multi-Class Classification

83% match2023

Improving Few-Shot Image Classification Using Machine- and User-Generated Natural Language Descriptions

83% match2022

Cite this paper

@article{milani2023towards,
  title  = {Towards One-Shot Learning for Text Classification using Inductive Logic Programming},
  author = {Ghazal Afroozi Milani and Daniel Cyrus and Alireza Tamaddoni-Nezhad},
  year   = {2023},
  eprint = {2308.15885},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2308.15885v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2308.15885.svg)](https://codeofpaper.com/paper/2308.15885)

Discussion