Data-to-text Generation with Macro Planning

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 th...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Transactions of the Association for Computational Linguistics Jg. 9; S. 510 - 527
Hauptverfasser: Puduppully, Ratish, Lapata, Mirella
Format: Journal Article
Sprache:Englisch
Veröffentlicht: One Rogers Street, Cambridge, MA 02142-1209, USA MIT Press 01.01.2021
MIT Press Journals, The
The MIT Press
Schlagworte:
Automatic text generation
Benchmarks
Computational linguistics
Data
Data collection
Datasets
Encoders-Decoders
Experiments
Linguistics
Neural networks
Planners
Planning
Professional baseball
Variants
ISSN:2307-387X, 2307-387X
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung: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.
Bibliographie:2021
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:2307-387X
2307-387X
DOI:10.1162/tacl_a_00381