Data-to-text Generation with Macro Planning

Mirella Lapata,Ratish Puduppully

doi:10.1162/tacl_a_00381

Mirella Lapata, Ratish Puduppully

Open Access

https://doi.org/10.1162/tacl_a_00381

Copy DOI

Abstract

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.

Highlights

Data-to-text generation refers to the task of generating textual output from non-linguistic input (Reiter and Dale, 1997, 2000; Gatt and Krahmer, 2018) such as databases of records, simulations of physical systems, accounting spreadsheets, or expert system knowledge bases
We found that Macro creates summaries which follow the plan closely: for ROTOWIRE, the Content Selection (CS) F-score and Content Ordering (CO) are greater than 98%; for major league baseball (MLB), the CS F-score is greater than 94% and CO is greater than 89%
In this work we presented a plan-and-generate approach for data-to-text generation which consists of a macro planning stage representing high-level document organization in terms of structure and content, followed by a text generation stage

Summary

Introduction

Data-to-text generation refers to the task of generating textual output from non-linguistic input (Reiter and Dale, 1997, 2000; Gatt and Krahmer, 2018) such as databases of records, simulations of physical systems, accounting spreadsheets, or expert system knowledge bases.

Methods

Results

Conclusion