@inbook{02cd7807a978441db9d0dce972625cd3,
title = "Exploring transformer text generation for medical dataset augmentation",
abstract = "Natural Language Processing (NLP) can help unlock the vast troves of unstructured data in clinical text and thus improve healthcare research. However, a big barrier to developments in this field is data access due to patient confidentiality which prohibits the sharing of this data, resulting in small, fragmented and sequestered openly available datasets. Since NLP model development requires large quantities of data, we aim to help side-step this roadblock by exploring the usage of Natural Language Generation in augmenting datasets such that they can be used for NLP model development on downstream clinically relevant tasks. We propose a methodology guiding the generation with structured patient information in a sequence-to-sequence manner. We experiment with state-of-the-art Transformer models and demonstrate that our augmented dataset is capable of beating our baselines on a downstream classification task. Finally, we also create a user interface and release the scripts to train generation models to stimulate further research in this area.",
keywords = "Ethics, Language Modelling, Legal Issues, Natural Language Generation",
author = "Ali Amin-Nejad and Julia Ive and Sumithra Velupillai",
year = "2020",
language = "English",
series = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
publisher = "European Language Resources Association (ELRA)",
pages = "4699--4708",
editor = "Nicoletta Calzolari and Frederic Bechet and Philippe Blache and Khalid Choukri and Christopher Cieri and Thierry Declerck and Sara Goggi and Hitoshi Isahara and Bente Maegaard and Joseph Mariani and Helene Mazo and Asuncion Moreno and Jan Odijk and Stelios Piperidis",
booktitle = "LREC 2020 - 12th International Conference on Language Resources and Evaluation, Conference Proceedings",
note = "12th International Conference on Language Resources and Evaluation, LREC 2020 ; Conference date: 11-05-2020 Through 16-05-2020",
}