Data-to-text Generation with Macro Planning
This work is significant for researchers and practitioners in natural language generation, as it offers an incremental improvement in generating more coherent and accurate text from structured data.
This paper addresses the issue of imprecise and incoherent text generation in data-to-text models by proposing a neural model with a macro planning stage. This approach, which learns high-level content organization from data and feeds it to a generator, outperforms competitive baselines on the RotoWire and MLB benchmarks.
Recent approaches to data-to-text generation have adopted the very successful encoder-decoder architecture or variants thereof. These models generate text which 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 learnt 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.