Data-to-text Generation with Macro Planning
Open Access
- 26 May 2021
- journal article
- research article
- Published by MIT Press in Transactions of the Association for Computational Linguistics
- Vol. 9, 510-527
Abstract
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 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 learned 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.Keywords
This publication has 31 references indexed in Scilit:
- Controlling Output Length in Neural Encoder-Decoders2016
- Neural Machine Translation of Rare Words with Subword Units2016
- Pointing the Unknown Words2016
- Effective Approaches to Attention-based Neural Machine Translation2015
- Long Short-Term MemoryNeural Computation, 1997
- Building applied natural language generation systemsNatural Language Engineering, 1997
- Language generation for multimedia healthcare briefings1997
- Automated discourse generation using discourse structure relationsArtificial Intelligence, 1993
- An Efficient Gradient-Based Algorithm for On-Line Training of Recurrent Network TrajectoriesNeural Computation, 1990
- Design of a knowledge-based report generator1983