Data-to-text Generation with Macro Planning

TL;DR

This paper introduces a neural data-to-text generation model with a macro planning stage that improves content selection and coherence, outperforming traditional encoder-decoder models on benchmark datasets.

Contribution

It proposes a novel neural architecture incorporating macro planning for better content organization in data-to-text generation.

Findings

Outperforms baseline models on RotoWire and MLB datasets.

Enhances content selection and coherence in generated text.

Achieves higher scores in automatic and human evaluations.

Abstract

Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which is fluent (but often imprecise) and perform quite poorly at selecting appropriate content and ordering it coherently. To overcome some of these issues, we propose a neural model with a macro planning stage followed by a generation stage reminiscent of traditional methods which embrace separate modules for planning and surface realization. Macro plans represent high level organization of important content such as entities, events and their interactions; they are learnt from data and given as input to the generator. Extensive experiments on two data-to-text benchmarks (RotoWire and MLB) show that our approach outperforms competitive baselines in terms of automatic and human evaluation.