arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2411.08397cs.CLcs.LG
收藏

CLaSP:从自然语言监督中学习时间序列信号的概念

CLaSP: Learning Concepts for Time-Series Signals from Natural Language Supervision

Hosei University(恒生大学);Hitachi Ltd.(日立株式会社)

Aoi Ito, Kota Dohi, Yohei Kawaguchi

AI总结:

本文提出CLaSP模型,利用对比学习将时间序列信号映射到自然语言描述,无需预定义词典,在TRUCE和SUSHI数据集上实现高精度检索。

摘要:

本文提出了CLaSP,一种新颖的模型,用于通过描述信号特征的自然语言查询来检索时间序列信号。在工业诊断等领域,数据科学家常常需要查找具有特定特征的信号,因此基于描述性查询搜索时间序列信号的能力至关重要。然而,现有方法依赖于基于草图的输入、预定义的同义词词典或特定领域的手工设计,限制了其可扩展性和适应性。CLaSP通过采用对比学习将时间序列信号映射到自然语言描述来解决这些挑战。与先前方法不同,它无需预定义的同义词词典,并利用大型语言模型(LLMs)丰富的上下文知识。使用TRUCE和SUSHI数据集(这些数据集将时间序列信号与自然语言描述配对),我们证明了CLaSP在基于自然语言查询检索各种时间序列模式方面实现了高准确性。

英文摘要:

This paper presents CLaSP, a novel model for retrieving time-series signals using natural language queries that describe signal characteristics. The ability to search time-series signals based on descriptive queries is essential in domains such as industrial diagnostics, where data scientists often need to find signals with specific characteristics. However, existing methods rely on sketch-based inputs, predefined synonym dictionaries, or domain-specific manual designs, limiting their scalability and adaptability. CLaSP addresses these challenges by employing contrastive learning to map time-series signals to natural language descriptions. Unlike prior approaches, it eliminates the need for predefined synonym dictionaries and leverages the rich contextual knowledge of large language models (LLMs). Using the TRUCE and SUSHI datasets, which pair time-series signals with natural language descriptions, we demonstrate that CLaSP achieves high accuracy in retrieving a variety of time series patterns based on natural language queries.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑