Data-to-text Generation with Macro Planning

• Published in: Transactions of the Association for Computational Linguistics Vol. 9; pp. 510 - 527
• Main Authors: Puduppully, Ratish, Lapata, Mirella
• Format: Journal Article
• Language: English
• Published: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.01.2021; MIT Press Journals, The; The MIT Press
• Subjects: Automatic text generation; Benchmarks; Computational linguistics; Datasets; Encoders-Decoders; Linguistics; Neural networks; Planning; Professional baseball
• ISSN: 2307-387X; 2307-387X
• DOI: 10.1162/tacl_a_00381

Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text that 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 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 learned from data and given as input to the generator. Extensive experiments on two data-to-text benchmarks ( and MLB) show that our approach outperforms competitive baselines in terms of automatic and human evaluation.