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

By Amit Moryossef, Ido Dagan, Yoav Goldberg. 2019

18 citations recorded by the source corpus.

We follow the step-by-step approach to neural data-to-text generation proposed by 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.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Natural Language Processing, Natural Language Generation

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Natural Language Processing

In Natural Language Generation

Citations in the corpus

DART: Open-Domain Structured Data Record to Text Generation (2020, methodology): “, 2019b) and NeuralPlan (Moryossef et al., 2019a) models, both of which use a step-by-step approach with a text-planning stage followed by a plan-realization stage on the WebNLG dataset.”
AggGen: Ordering and Aggregating while Generating (2021, background): “For example, in (Moryossef et al., 2019b; Zhao et al., 2020) the sentence plan is created independently, incurring error propagation; Wiseman et al. (2018) use latent segmentation that limits interpretability; Shao et al. (2019) sample from a latent variable, not allowing for explicit control; and…”
Bridging the Structural Gap Between Encoding and Decoding for Data-To-Text Generation (2020, unknown): “The activation function is ReLU (Nair and Hinton, 2010).”
Have Your Text and Use It Too! End-to-End Neural Data-to-Text Generation with Semantic Fidelity (2020, background): “Another approach has been to rely on heuristics that map data values to potential realizations in the text, thus computing a Slot Error Rate (SER) metric (Duˇsek et al., 2019; Juraska et al., 2019; Moryossef et al., 2019a).”
Control Prefixes for Parameter-Efficient Text Generation (2021, background): “The intuition of the category providing useful information is supported by studies showing a clear disparity in the performance of different model types between different categories (Moryossef et al., 2019; Castro Ferreira et al., 2020).”
Towards Faithfulness in Open Domain Table-to-text Generation from an Entity-centric View (2021, methodology): “Our paper focuses on a two-stage generation which incorporate separate text planner (Ferreira et al. 2019; Moryossef, Dagan, and Goldberg 2019; Ma et al. 2019).”
Control Prefixes for Text Generation (2021, background): “This idea is encouraged by studies where there is a clear disparity in performance on different categories between different model types (Moryossef et al., 2019; Castro Ferreira et al., 2020).”