arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2407.12833cs.CLcs.LG
收藏

ESQA:事件序列问答

ESQA: Event Sequences Question Answering

AIRI;Sber AI;Skoltech(斯科尔泰克理工学院);Sber AI Lab(Sber AI实验室);MIPT(莫斯科物理技术学院)

Irina Abdullaeva, Andrei Filatov, Mikhail Orlov, Ivan Karpukhin, Viacheslav Vasilev, Denis Dimitrov, Andrey Kuznetsov, Ivan Kireev, Andrey Savchenko

AI总结:

本文提出ESQA方法,利用大型语言模型解决事件序列问答中的长序列与时间数值特征处理难题,无需或少量微调即可完成多任务,实验达到领域最先进水平。

摘要:

事件序列(ESs)出现在许多实际领域中,包括金融、零售、社交网络和医疗保健。在机器学习的背景下,事件序列可以被视为带有注释时间戳的特殊类型的表格数据。尽管事件序列建模和分析很重要,但在将大型语言模型(LLMs)适应于事件序列领域方面所做的努力很少。在本文中,我们强调了事件序列处理的常见困难,并提出了一种新颖的解决方案,能够以很少或无需微调的方式解决多个下游任务。特别是,我们解决了处理长序列的问题,并改进了时间和数值特征的处理。所得到的方法称为ESQA,有效地利用了LLMs的能力,并且根据大量实验,在事件序列领域取得了最先进的结果。

英文摘要:

Event sequences (ESs) arise in many practical domains including finance, retail, social networks, and healthcare. In the context of machine learning, event sequences can be seen as a special type of tabular data with annotated timestamps. Despite the importance of ESs modeling and analysis, little effort was made in adapting large language models (LLMs) to the ESs domain. In this paper, we highlight the common difficulties of ESs processing and propose a novel solution capable of solving multiple downstream tasks with little or no finetuning. In particular, we solve the problem of working with long sequences and improve time and numeric features processing. The resulting method, called ESQA, effectively utilizes the power of LLMs and, according to extensive experiments, achieves state-of-the-art results in the ESs domain.

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。

↑