Towards One-Shot Learning for Text Classification using Inductive Logic Programming
Not on the map. Why?
Abstract (arXiv)
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.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 8 of its 27 references that are in the map. First posted on arXiv 30 Aug 2023.
Builds on
8 of 27 references.
References · 8
- 2016ConceptNet 5.5: An Open Multilingual Graph of General Knowledgecited by 1,067
- 2020Inductive logic programming at 30: a new introductioncited by 85
- 2022News Category Datasetcited by 43
- 2021Dimensions of Commonsense Knowledgecited by 29
- 2020Inductive Learning on Commonsense Knowledge Graph Completioncited by 22
- 2019Logical reduction of metarulescited by 19
- 2020Semantic Networks for Engineering Design: A Surveycited by 6
- 2021Meta-Interpretive Learning as Metarule Specialisationcited by 2
Built on by
Not cited yet.