Denoising Pre-Training and Data Augmentation Strategies for Enhanced RDF Verbalization with Transformers

by   Sebastien Montella, et al.

The task of verbalization of RDF triples has known a growth in popularity due to the rising ubiquity of Knowledge Bases (KBs). The formalism of RDF triples is a simple and efficient way to store facts at a large scale. However, its abstract representation makes it difficult for humans to interpret. For this purpose, the WebNLG challenge aims at promoting automated RDF-to-text generation. We propose to leverage pre-trainings from augmented data with the Transformer model using a data augmentation strategy. Our experiment results show a minimum relative increases of 3.73 for seen categories, unseen entities and unseen categories respectively over the standard training.


page 1

page 2

page 3

page 4


Data augmentation enhanced speaker enrollment for text-dependent speaker verification

Data augmentation is commonly used for generating additional data from t...

Sequence-to-sequence Pre-training with Data Augmentation for Sentence Rewriting

We study sequence-to-sequence (seq2seq) pre-training with data augmentat...

MixGen: A New Multi-Modal Data Augmentation

Data augmentation is a necessity to enhance data efficiency in deep lear...

Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR

Recently Deep Transformer models have proven to be particularly powerful...

PHICON: Improving Generalization of Clinical Text De-identification Models via Data Augmentation

De-identification is the task of identifying protected health informatio...