Retrieval of Temporal Event Sequences from Textual Descriptions
This work addresses the need for analyzing temporal event sequences in applications like e-commerce and social media, though it appears incremental as it builds on existing TPP and LLM frameworks.
The paper tackles the problem of retrieving temporal event sequences from textual descriptions by introducing TESRBench, a comprehensive benchmark, and TPP-Embedding, a novel model that integrates LLMs with TPPs to encode event texts and times, achieving superior performance over baseline models on the benchmark datasets.
Retrieving temporal event sequences from textual descriptions is crucial for applications such as analyzing e-commerce behavior, monitoring social media activities, and tracking criminal incidents. To advance this task, we introduce TESRBench, a comprehensive benchmark for temporal event sequence retrieval (TESR) from textual descriptions. TESRBench includes diverse real-world datasets with synthesized and reviewed textual descriptions, providing a strong foundation for evaluating retrieval performance and addressing challenges in this domain. Building on this benchmark, we propose TPP-Embedding, a novel model for embedding and retrieving event sequences. The model leverages the TPP-LLM framework, integrating large language models (LLMs) with temporal point processes (TPPs) to encode both event texts and times. By pooling representations and applying a contrastive loss, it unifies temporal dynamics and event semantics in a shared embedding space, aligning sequence-level embeddings of event sequences and their descriptions. TPP-Embedding demonstrates superior performance over baseline models across TESRBench datasets, establishing it as a powerful solution for the temporal event sequence retrieval task.