Improving Quality and Efficiency in Plan-based Neural Data-to-Text Generation

09/22/2019
by   Amit Moryossef, et al.
0

We follow the step-by-step approach to neural data-to-text generation we proposed in Moryossef et al (2019), in which the generation process is divided into a text-planning stage followed by a plan-realization stage. We suggest four extensions to that framework: (1) we introduce a trainable neural planning component that can generate effective plans several orders of magnitude faster than the original planner; (2) we incorporate typing hints that improve the model's ability to deal with unseen relations and entities; (3) we introduce a verification-by-reranking stage that substantially improves the faithfulness of the resulting texts; (4) we incorporate a simple but effective referring expression generation module. These extensions result in a generation process that is faster, more fluent, and more accurate.

READ FULL TEXT
research
04/06/2019

Step-by-Step: Separating Planning from Realization in Neural Data-to-Text Generation

Data-to-text generation can be conceptually divided into two parts: orde...
research
02/04/2021

Data-to-text Generation with Macro Planning

Recent approaches to data-to-text generation have adopted the very succe...
research
08/31/2021

Plan-then-Generate: Controlled Data-to-Text Generation via Planning

Recent developments in neural networks have led to the advance in data-t...
research
08/19/2019

Long and Diverse Text Generation with Planning-based Hierarchical Variational Model

Existing neural methods for data-to-text generation are still struggling...
research
01/07/2023

Graph-based Keyword Planning for Legal Clause Generation from Topics

Generating domain-specific content such as legal clauses based on minima...
research
08/18/2021

GGP: A Graph-based Grouping Planner for Explicit Control of Long Text Generation

Existing data-driven methods can well handle short text generation. Howe...
research
06/28/2023

You Can Generate It Again: Data-to-text Generation with Verification and Correction Prompting

Despite significant advancements in existing models, generating text des...

Please sign up or login with your details

Forgot password? Click here to reset