Data-to-Text Generation with Content Selection and Planning

• DOI: 10.1609/aaai.v33i01.33016908
• Publication Date: 2019-08-25T07:43:38Z
• Authors: Ratish Puduppully; Li Dong; Mirella Lapata
• Keywords: Content (measure theory); Text generation

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 what say order. In this work, we present a architecture incorporates content selection planning sacrificing end-to-end training. We decompose task into two stages. Given corpus data records (paired with descriptive documents), first generate plan highlighting information should be mentioned order then document while taking account. Automatic human-based evaluation experiments show that our model1 outperforms strong baselines improving state-of-the-art on recently released RotoWIRE dataset.