# Variational Template Machine for Data-to-Text Generation

Source: [Variational Template Machine for Data-to-Text Generation](<https://www.sota2.com/research/paper/68fa67081e209131cea13fc1>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-01-04T03:11:48.949Z

Authors: Rong Ye, Wenxian Shi, Hao Zhou, Zhongyu Wei, Lei Li

Published: 2020-02-04T04:53:45.000Z

## Abstract

How to generate descriptions from structured data organized in tables? Existing approaches using neural encoder-decoder models often suffer from lacking diversity. We claim that an open set of templates is crucial for enriching the phrase constructions and realizing varied generations. Learning such templates is prohibitive since it often requires a large paired \<table, description\> corpus, which is seldom available. This paper explores the problem of automatically learning reusable "templates" from paired and non-paired data. We propose the variational template machine (VTM), a novel method to generate text descriptions from data tables. Our contributions include: a) we carefully devise a specific model architecture and losses to explicitly disentangle text template and semantic content information, in the latent spaces, and b)we utilize both small parallel data and large raw text without aligned tables to enrich the template learning. Experiments on datasets from a variety of different domains show that VTM is able to generate more diversely while keeping a good fluency and quality.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

- [Data-to-Text Generation on SPNLG](<https://www.sota2.com/research/sota/data-to-text-generation-on-spnlg.md>): Data-to-text generation; SPNLG; Accuracy: 4.44.

- [Data-to-text generation on SPNLG (test)](<https://www.sota2.com/research/sota/data-to-text-generation-on-spnlg-test.md>): Data-to-text generation; SPNLG (test); BLEU: 40.04.

- [Table-to-text generation on WIKI dataset (test)](<https://www.sota2.com/research/sota/table-to-text-generation-on-wiki-dataset-test.md>): Table-to-text generation; WIKI dataset (test); BLEU: 25.22.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2002.01127>)

[PDF](<https://arxiv.org/pdf/2002.01127.pdf>)