TabGenie: A Toolkit for Table-to-Text Generation
This toolkit addresses the need for researchers in natural language processing to work with diverse datasets more efficiently, though it is incremental as it builds on existing table-to-text frameworks.
The authors tackled the problem of heterogeneity in data-to-text generation datasets by developing TabGenie, a toolkit that unifies table-to-text generation, enabling exploration, preprocessing, and analysis through a web interface and command-line tools.
Heterogenity of data-to-text generation datasets limits the research on data-to-text generation systems. We present TabGenie - a toolkit which enables researchers to explore, preprocess, and analyze a variety of data-to-text generation datasets through the unified framework of table-to-text generation. In TabGenie, all the inputs are represented as tables with associated metadata. The tables can be explored through the web interface, which also provides an interactive mode for debugging table-to-text generation, facilitates side-by-side comparison of generated system outputs, and allows easy exports for manual analysis. Furthermore, TabGenie is equipped with command line processing tools and Python bindings for unified dataset loading and processing. We release TabGenie as a PyPI package and provide its open-source code and a live demo at https://github.com/kasnerz/tabgenie.