AGGGEN: Ordering and Aggregating while Generating

TL;DR

AGGGEN is a neural data-to-text model that integrates explicit sentence planning stages, such as input ordering and aggregation, into end-to-end generation, improving interpretability and robustness.

Contribution

It introduces a novel end-to-end neural model that explicitly incorporates sentence planning through latent alignments, enhancing interpretability and control.

Findings

More interpretable and expressive generation

Robustness to noise and easier control

Maintains fluency of end-to-end systems

Abstract

We present AGGGEN (pronounced 'again'), a data-to-text model which re-introduces two explicit sentence planning stages into neural data-to-text systems: input ordering and input aggregation. In contrast to previous work using sentence planning, our model is still end-to-end: AGGGEN performs sentence planning at the same time as generating text by learning latent alignments (via semantic facts) between input representation and target text. Experiments on the WebNLG and E2E challenge data show that by using fact-based alignments our approach is more interpretable, expressive, robust to noise, and easier to control, while retaining the advantages of end-to-end systems in terms of fluency. Our code is available at https://github.com/XinnuoXu/AggGen.