Towards Time Series Generation Conditioned on Unstructured Natural Language

TL;DR

This paper introduces a novel diffusion-based method for generating time series data conditioned on unstructured natural language, enabling applications like forecasting, manipulation, and data augmentation, supported by a new large dataset.

Contribution

The paper presents a new approach combining diffusion and language models for time series generation from text, and introduces a large public dataset for this task.

Findings

Time series can be generated from natural language descriptions.

The method enables applications like forecasting and data augmentation.

A new dataset with over 63,000 time series-description pairs is provided.

Abstract

Generative Artificial Intelligence (AI) has rapidly become a powerful tool, capable of generating various types of data, such as images and text. However, despite the significant advancement of generative AI, time series generative AI remains underdeveloped, even though the application of time series is essential in finance, climate, and numerous fields. In this research, we propose a novel method of generating time series conditioned on unstructured natural language descriptions. We use a diffusion model combined with a language model to generate time series from the text. Through the proposed method, we demonstrate that time series generation based on natural language is possible. The proposed method can provide various applications such as custom forecasting, time series manipulation, data augmentation, and transfer learning. Furthermore, we construct and propose a new public dataset for time series generation, consisting of 63,010 time series-description pairs.