TY - JOUR AU - Puduppully, Ratish AU - Dong, Li AU - Lapata, Mirella PY - 2019/07/17 Y2 - 2024/03/28 TI - Data-to-Text Generation with Content Selection and Planning JF - Proceedings of the AAAI Conference on Artificial Intelligence JA - AAAI VL - 33 IS - 01 SE - AAAI Technical Track: Natural Language Processing DO - 10.1609/aaai.v33i01.33016908 UR - https://ojs.aaai.org/index.php/AAAI/article/view/4668 SP - 6908-6915 AB - <p>Recent advances in data-to-text generation have led to the use of large-scale datasets and neural network models which are trained end-to-end, without explicitly modeling <em>what to say</em> and <em>in what order</em>. In this work, we present a neural network architecture which incorporates content selection and planning without sacrificing end-to-end training. We decompose the generation task into two stages. Given a corpus of data records (paired with descriptive documents), we first generate a content plan highlighting which information should be mentioned and in which order and then generate the document while taking the content plan into account. Automatic and human-based evaluation experiments show that our model<sup>1</sup> outperforms strong baselines improving the state-of-the-art on the recently released R<span style="font-variant: small-caps;">oto</span>W<span style="font-variant: small-caps;">IRE</span> dataset.</p> ER -