# Data-to-text Generation with Entity Modeling

## TL;DR

This paper introduces an entity-centric neural model for data-to-text generation that dynamically updates entity representations, leading to improved performance on benchmarks and a new baseball dataset.

## Contribution

The work presents a novel entity-focused neural architecture with dynamic entity representations and hierarchical attention, advancing data-to-text generation methods.

## Key findings

- Outperforms baseline models on RotoWire benchmark
- Achieves better human evaluation scores
- Effective on a new large baseball dataset

## Abstract

Recent approaches to data-to-text generation have shown great promise thanks to the use of large-scale datasets and the application of neural network architectures which are trained end-to-end. These models rely on representation learning to select content appropriately, structure it coherently, and verbalize it grammatically, treating entities as nothing more than vocabulary tokens. In this work we propose an entity-centric neural architecture for data-to-text generation. Our model creates entity-specific representations which are dynamically updated. Text is generated conditioned on the data input and entity memory representations using hierarchical attention at each time step. We present experiments on the RotoWire benchmark and a (five times larger) new dataset on the baseball domain which we create. Our results show that the proposed model outperforms competitive baselines in automatic and human evaluation.