# HEIDL: Learning Linguistic Expressions with Deep Learning and Human-in-the-Loop

## TL;DR

HEIDL introduces a high-level, explainable linguistic model interface for human-in-the-loop machine learning, enabling direct interpretation and updating of model logic to improve text analytics and generalization.

## Contribution

This work presents HEIDL, a novel HITL-ML system that elevates human interaction to semantic levels, enhancing model interpretability and domain expertise integration.

## Key findings

- Human interaction at semantic levels improves model understanding.
- Involving humans leads to better generalization on unseen data.
- Semantic interaction paradigms increase productivity in text analytics.

## Abstract

While the role of humans is increasingly recognized in machine learning community, representation of and interaction with models in current human-in-the-loop machine learning (HITL-ML) approaches are too low-level and far-removed from human's conceptual models. We demonstrate HEIDL, a prototype HITL-ML system that exposes the machine-learned model through high-level, explainable linguistic expressions formed of predicates representing semantic structure of text. In HEIDL, human's role is elevated from simply evaluating model predictions to interpreting and even updating the model logic directly by enabling interaction with rule predicates themselves. Raising the currency of interaction to such semantic levels calls for new interaction paradigms between humans and machines that result in improved productivity for text analytics model development process. Moreover, by involving humans in the process, the human-machine co-created models generalize better to unseen data as domain experts are able to instill their expertise by extrapolating from what has been learned by automated algorithms from few labelled data.