Towards One-Shot Learning for Text Classification using Inductive Logic Programming
This addresses the need for personalized AI tasks with limited data, though it appears incremental as it applies existing methods to a specific domain.
The paper tackles the problem of data-efficient text classification by exploring an Inductive Logic Programming approach using Meta-Interpretive Learning with ConceptNet background knowledge, showing it can learn rules from few examples with accuracy improving with example complexity.
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.