Towards Neural Numeric-To-Text Generation From Temporal Personal Health Data

TL;DR

This paper explores neural network models including recurrent, convolutional, and Transformer-based architectures to automatically generate natural language summaries from personal health time-series data, aiming to enhance behavioral insights.

Contribution

It introduces neural encoder-decoder models for health data summarization, moving beyond rule-based methods, and demonstrates their effectiveness on real user data from MyFitnessPal.

Findings

Neural models outperform rule-based approaches.

High-quality natural language summaries generated.

Effective on real-world personal health data.

Abstract

With an increased interest in the production of personal health technologies designed to track user data (e.g., nutrient intake, step counts), there is now more opportunity than ever to surface meaningful behavioral insights to everyday users in the form of natural language. This knowledge can increase their behavioral awareness and allow them to take action to meet their health goals. It can also bridge the gap between the vast collection of personal health data and the summary generation required to describe an individual's behavioral tendencies. Previous work has focused on rule-based time-series data summarization methods designed to generate natural language summaries of interesting patterns found within temporal personal health data. We examine recurrent, convolutional, and Transformer-based encoder-decoder models to automatically generate natural language summaries from numeric temporal personal health data. We showcase the effectiveness of our models on real user health data logged in MyFitnessPal and show that we can automatically generate high-quality natural language summaries. Our work serves as a first step towards the ambitious goal of automatically generating novel and meaningful temporal summaries from personal health data.