# Natural Language Models for Data Visualization Utilizing nvBench Dataset

arXiv: https://arxiv.org/abs/2310.00832 · HTML: https://mlsanity.com/paper/2310.00832/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 10 references that are in the map.
- First posted on arXiv 2 Oct 2023.

## Builds on (most cited first, 5 of 5)

- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [CodeT5: Identifier-aware Unified Pre-trained Encoder-Decoder Models for Code Understanding and Generation](https://mlsanity.com/paper/2109.00859/) (2021)
- [Seq2SQL: Generating Structured Queries from Natural Language using Reinforcement Learning](https://mlsanity.com/paper/1709.00103/) (2017)
- [CoSQL: A Conversational Text-to-SQL Challenge Towards Cross-Domain Natural Language Interfaces to Databases](https://mlsanity.com/paper/1909.05378/) (2019)
- [nvBench: A Large-Scale Synthesized Dataset for Cross-Domain Natural Language to Visualization Task](https://mlsanity.com/paper/2112.12926/) (2021)

## Built on by (most cited first, 3 of 3)

- [CoDA: Agentic Systems for Collaborative Data Visualization](https://mlsanity.com/paper/2510.03194/) (2025)
- [Sparks of Tabular Reasoning via Text2SQL Reinforcement Learning](https://mlsanity.com/paper/2505.00016/) (2025)
- [STRuCT-LLM: Unifying Tabular and Graph Reasoning with Reinforcement Learning for Semantic Parsing](https://mlsanity.com/paper/2506.21575/) (2025)

## Abstract (arXiv)

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 suppliedciteZhong: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.