Language-TPP: Integrating Temporal Point Processes with Language Models for Event Analysis
This work addresses the gap between textual and temporal modeling for event analysis, offering a unified solution that could benefit domains like healthcare or finance, though it appears incremental by hybridizing existing methods.
The paper tackled the problem of integrating rich textual event descriptions with temporal dynamics in event sequence modeling by introducing Language-TPP, a framework that combines Temporal Point Processes with Large Language Models, achieving state-of-the-art performance on tasks like event time prediction across five datasets.
Temporal Point Processes (TPPs) have been widely used for event sequence modeling, but they often struggle to incorporate rich textual event descriptions effectively. Conversely, while Large Language Models (LLMs) have been shown remarkable capabilities in processing textual data, they lack mechanisms for handling temporal dynamics. To bridge this gap, we introduce Language-TPP, a unified framework that integrates TPPs with LLMs for enhanced event sequence modeling. Language-TPP introduces a novel temporal encoding mechanism that converts continuous time intervals into specialized byte-tokens, enabling seamless integration with standard LLM architectures. This approach allows Language-TPP to achieve state-of-the-art performance across multiple TPP tasks, including event time prediction, type prediction, and intensity estimation, on five datasets. Additionally, we demonstrate that incorporating temporal information significantly improves the quality of generated event descriptions.