We propose an algorithm for next query recommendation in interactive data exploration settings, like knowledge discovery for information gathering. The state-of-the-art query recommendation algorithms are based on sequence-to-sequence learning approaches that exploit historical interaction data. We propose to augment the transformer-based causal language models for query recommendations to adapt to the immediate user feedback using multi-armed bandit (MAB) framework. We conduct a large-scale experimental study using log files from a popular online literature discovery service and demonstrate that our algorithm improves the cumulative regret substantially, with respect to the state-of-the-art transformer-based query recommendation models, which do not make use of the immediate user feedback. Our data model and source code are available at ~\url{https://anonymous.4open.science/r/exp3_ss-9985/}.
翻译:在交互式数据探索环境中,我们提出下一个查询建议的算法,例如为收集信息而发现知识; 最新查询建议算法以利用历史互动数据的顺序到顺序学习方法为基础; 我们提议增加基于变压器的因果语言模式,以便利用多武装土匪(MAB)框架对查询建议进行调整,以适应用户的即时反馈; 我们利用流行在线文献发现服务的日志文件进行大规模实验研究,并表明我们的算法大大改善了基于最新变压器的查询建议模式的累积遗憾,这些模式不使用即时用户反馈; 我们的数据模型和源代码可在 url{https://anonnymous.4open.science/r/explic3_s-9985/}查阅。