# Comparing Computational Architectures for Automated Journalism

arXiv: https://arxiv.org/abs/2210.04107 · HTML: https://mlsanity.com/paper/2210.04107/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 36 references that are in the map.
- First posted on arXiv 8 Oct 2022.

## Builds on (most cited first, 9 of 9)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [mT5: A massively multilingual pre-trained text-to-text transformer](https://mlsanity.com/paper/2010.11934/) (2020)
- [On the Properties of Neural Machine Translation: Encoder-Decoder Approaches](https://mlsanity.com/paper/1409.1259/) (2014)
- [Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation](https://mlsanity.com/paper/1703.09902/) (2017)
- [BlenderBot 3: a deployed conversational agent that continually learns to responsibly engage](https://mlsanity.com/paper/2208.03188/) (2022)
- [Neural data-to-text generation: A comparison between pipeline and end-to-end architectures](https://mlsanity.com/paper/1908.09022/) (2019)
- [Findings of the E2E NLG Challenge](https://mlsanity.com/paper/1810.01170/) (2018)
- [Attention Is Indeed All You Need: Semantically Attention-Guided Decoding for Data-to-Text NLG](https://mlsanity.com/paper/2109.07043/) (2021)
- [Tracking Naturalistic Linguistic Predictions with Deep Neural Language Models](https://mlsanity.com/paper/1909.04400/) (2019)

## Abstract (arXiv)

The majority of NLG systems have been designed following either a template-based or a pipeline-based architecture. Recent neural models for data-to-text generation have been proposed with an end-to-end deep learning flavor, which handles non-linguistic input in natural language without explicit intermediary representations. This study compares the most often employed methods for generating Brazilian Portuguese texts from structured data. Results suggest that explicit intermediate steps in the generation process produce better texts than the ones generated by neural end-to-end architectures, avoiding data hallucination while better generalizing to unseen inputs. Code and corpus are publicly available.