Ecosyste.ms: Awesome

An open API service indexing awesome lists of open source software.

Awesome Lists | Featured Topics | Projects

https://github.com/nl4dv/nl4dv

A python toolkit to create Visualizations (Vis) using natural language (NL) or add an NL interface to existing Vis.
https://github.com/nl4dv/nl4dv

conversational conversational-interaction conversational-interactions data-visualization datascience jupyter-notebook natural-language natural-language-interface natural-language-processing nl-interface opensource python toolkit vega-lite visualization

Last synced: 8 days ago
JSON representation

A python toolkit to create Visualizations (Vis) using natural language (NL) or add an NL interface to existing Vis.

Host: GitHub
URL: https://github.com/nl4dv/nl4dv
Owner: nl4dv
License: mit
Created: 2020-04-30T21:50:18.000Z (over 4 years ago)
Default Branch: master
Last Pushed: 2024-10-21T20:48:21.000Z (15 days ago)
Last Synced: 2024-10-22T08:25:14.878Z (15 days ago)
Topics: conversational, conversational-interaction, conversational-interactions, data-visualization, datascience, jupyter-notebook, natural-language, natural-language-interface, natural-language-processing, nl-interface, opensource, python, toolkit, vega-lite, visualization
Language: Python
Homepage: https://nl4dv.github.io
Size: 24.9 MB
Stars: 136
Watchers: 4
Forks: 23
Open Issues: 2
Metadata Files:
- Readme: README.md
- License: LICENSE

Awesome Lists containing this project

awesome-viz - NL4DV - Natural Language toolkit for Data Visualization. It takes a natural language query about a given dataset as input and outputs a structured JSON object containing: (1) Data attributes, (2) Analytic tasks, and (3) Visualizations (Vega-Lite specifications). The [showcase](https://nl4dv.github.io/nl4dv/showcase.html) shows example use cases and applications. [Presented](https://youtu.be/U5uDyILweu8) at IEEE VIS 2020. (Also No Code) ([↑](#contents) Declarative)

README

        # NL4DV: **N**atural **L**anguage toolkit **for** **D**ata **V**isualization

[![DOI:10.1109/TVCG.2020.3030418](https://zenodo.org/badge/DOI/10.1109/TVCG.2020.3030378.svg)](https://doi.org/10.1109/TVCG.2020.3030378)

[![arxiv badge](https://img.shields.io/badge/arXiv-2008.10723-red)](https://arxiv.org/abs/2008.10723)

[![arxiv badge](https://img.shields.io/badge/arXiv-2207.00189-%23B31B1B)](https://arxiv.org/abs/2207.00189)

[![PyPI license](https://img.shields.io/pypi/l/ansicolortags.svg)](https://pypi.python.org/pypi/nl4dv/)

![PyPI - Downloads](https://img.shields.io/pypi/dm/nl4dv)

**NL4DV** takes a **natural language query** about a given **dataset** as input and outputs a **structured JSON object** containing:

* Data attributes,

* Analytic tasks, and

* Visualizations (Vega-Lite specifications)

With this output, developers can

  - Create visualizations in Python using natural language, and/or

  - Add a natural language interface to their existing visualization systems.

![NL4DV Overview](https://raw.githubusercontent.com/nl4dv/nl4dv/master/overview.gif)

### Setup Instructions, API Documentation, and Examples

These can all be found on [NL4DV's project website](https://nl4dv.github.io/nl4dv/documentation.html).

### Credits

NL4DV was created by

Arpit Narechania, Arjun Srinivasan, Rishab Mitra, Alex Endert, and John Stasko of the Georgia Tech Visualization Lab. Along with Subham Sah, and Wenwen Dou of the Ribarsky Center for Visual Analytics at UNC Charlotte.

We thank the members of the Georgia Tech Visualization Lab for their support and constructive feedback.

### Citations

#### 2021 IEEE TVCG Journal Full Paper (Proceedings of the 2020 IEEE VIS Conference)

```bibTeX

@article{narechania2021nl4dv,

  title = {{NL4DV}: A {Toolkit} for Generating {Analytic Specifications} for {Data Visualization} from {Natural Language} Queries},

  shorttitle = {{NL4DV}},

  author = {{Narechania}, Arpit and {Srinivasan}, Arjun and {Stasko}, John},

  journal = {IEEE Transactions on Visualization and Computer Graphics (TVCG)},

  doi = {10.1109/TVCG.2020.3030378},

  year = {2021},

  publisher = {IEEE}

}

```

#### 2022 IEEE VIS Conference Short Paper Track

```bibTeX

@inproceedings{mitra2022conversationalinteraction,

  title = {{Facilitating Conversational Interaction in Natural Language Interfaces for Visualization}},

  author = {{Mitra}, Rishab and {Narechania}, Arpit and {Endert}, Alex and {Stasko}, John},

  booktitle={2022 IEEE Visualization Conference (VIS)},

  url = {https://doi.org/10.48550/arXiv.2207.00189},

  doi = {10.48550/arXiv.2207.00189},

  year = {2022},

  publisher = {IEEE}

}

```

#### 2024 IEEE VIS NLVIZ workshop Paper

```bibTeX

@misc{sah2024nl4dvllm,

    title={Generating Analytic Specifications for Data Visualization from Natural Language Queries using Large Language Models}, 

    author={Subham Sah and Rishab Mitra and Arpit Narechania and Alex Endert and John Stasko and Wenwen Dou},

    year={2024},

    eprint={2408.13391},

    archivePrefix={arXiv},

    primaryClass={cs.HC},

    url={https://arxiv.org/abs/2408.13391}, 

    howpublished={Presented at the NLVIZ Workshop, IEEE VIS 2024}

}

```

### License

The software is available under the [MIT License](https://github.com/nl4dv/nl4dv/blob/master/LICENSE).

### Contact

If you have any questions, feel free to [open an issue](https://github.com/nl4dv/nl4dv/issues/new/choose) or contact [Arpit Narechania](http://narechania.com).