# Two Birds, One Stone: A Simple, Unified Model for Text Generation from Structured and Unstructured Data

arXiv: https://arxiv.org/abs/1909.10158 · HTML: https://mlsanity.com/paper/1909.10158/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2019.

## Built on by (most cited first, 6 of 6)

- [Probing Product Description Generation via Posterior Distillation](https://mlsanity.com/paper/2103.01594/) (2021)
- [LOGEN: Few-shot Logical Knowledge-Conditioned Text Generation with Self-training](https://mlsanity.com/paper/2112.01404/) (2021)
- [XAlign: Cross-lingual Fact-to-Text Alignment and Generation for Low-Resource Languages](https://mlsanity.com/paper/2202.00291/) (2022)
- [PATS: Sensitivity-aware Noisy Learning for Pretrained Language Models](https://mlsanity.com/paper/2210.12403/) (2022)
- [XF2T: Cross-lingual Fact-to-Text Generation for Low-Resource Languages](https://mlsanity.com/paper/2209.11252/) (2022)
- [XWikiGen: Cross-lingual Summarization for Encyclopedic Text Generation in Low Resource Languages](https://mlsanity.com/paper/2303.12308/) (2023)

## Abstract (arXiv)

A number of researchers have recently questioned the necessity of increasingly complex neural network (NN) architectures. In particular, several recent papers have shown that simpler, properly tuned models are at least competitive across several NLP tasks. In this work, we show that this is also the case for text generation from structured and unstructured data. We consider neural table-to-text generation and neural question generation (NQG) tasks for text generation from structured and unstructured data, respectively. Table-to-text generation aims to generate a description based on a given table, and NQG is the task of generating a question from a given passage where the generated question can be answered by a certain sub-span of the passage using NN models. Experimental results demonstrate that a basic attention-based seq2seq model trained with the exponential moving average technique achieves the state of the art in both tasks. Code is available at https://github.com/h-shahidi/2birds-gen.