# NeuralREG: An end-to-end approach to referring expression generation

arXiv: https://arxiv.org/abs/1805.08093 · HTML: https://mlsanity.com/paper/1805.08093/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 May 2018.

## Built on by (most cited first, 7 of 7)

- [Innovations in Neural Data-to-text Generation: A Survey](https://mlsanity.com/paper/2207.12571/) (2022)
- [Non-neural Models Matter: A Re-evaluation of Neural Referring Expression Generation Systems](https://mlsanity.com/paper/2203.08274/) (2022)
- [What can Neural Referential Form Selectors Learn?](https://mlsanity.com/paper/2108.06806/) (2021)
- [Models of reference production: How do they withstand the test of time?](https://mlsanity.com/paper/2307.14817/) (2023)
- [Changing the Narrative Perspective: From Deictic to Anaphoric Point of View](https://mlsanity.com/paper/2103.04176/) (2021)
- [Assessing Neural Referential Form Selectors on a Realistic Multilingual Dataset](https://mlsanity.com/paper/2210.04828/) (2022)
- [Intrinsic Task-based Evaluation for Referring Expression Generation](https://mlsanity.com/paper/2402.07432/) (2024)

## Abstract (arXiv)

Traditionally, Referring Expression Generation (REG) models first decide on the form and then on the content of references to discourse entities in text, typically relying on features such as salience and grammatical function. In this paper, we present a new approach (NeuralREG), relying on deep neural networks, which makes decisions about form and content in one go without explicit feature extraction. Using a delexicalized version of the WebNLG corpus, we show that the neural model substantially improves over two strong baselines. Data and models are publicly available.