利用nvBench数据集的面向数据可视化的自然语言模型
Natural Language Models for Data Visualization Utilizing nvBench Dataset
AI总结:
本研究利用nvBench数据集,构建基于序列到序列transformer、以BERT为编码器的自然语言翻译模型,将自然语言转为Vega Zero可视化命令,并与T5模型对比,推动数据可视化翻译研究。
摘要:
将自然语言翻译成语法正确的数据可视化命令是自然语言模型的一项重要应用,可用于多种不同任务。一项密切相关的研究是将自然语言翻译成SQL查询的任务,这类查询可借助自然语言查询提供的额外信息进一步转化为可视化结果\cite{Zhong:2017qr}。为推动该领域研究进展,我们构建了自然语言翻译模型,用以生成名为Vega Zero的语言编写的简化版数据与可视化查询。本文探究了基于序列到序列transformer的机器学习模型架构的设计与性能,这类架构采用BERT等大语言模型作为编码器,从自然语言查询预测可视化命令,同时我们还将现有T5序列到序列模型应用于该问题以作对比。
英文摘要:
Translation of natural language into syntactically correct commands for data visualization is an important application of natural language models and could be leveraged to many different tasks. A closely related effort is the task of translating natural languages into SQL queries, which in turn could be translated into visualization with additional information from the natural language query supplied\cite{Zhong:2017qr}. Contributing to the progress in this area of research, we built natural language translation models to construct simplified versions of data and visualization queries in a language called Vega Zero. In this paper, we explore the design and performance of these sequence to sequence transformer based machine learning model architectures using large language models such as BERT as encoders to predict visualization commands from natural language queries, as well as apply available T5 sequence to sequence models to the problem for comparison.
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。