Biomedical Data-to-Text Generation via Fine-Tuning Transformers
Machine Learning
2021-09-06 v1 Computation and Language
Abstract
Data-to-text (D2T) generation in the biomedical domain is a promising - yet mostly unexplored - field of research. Here, we apply neural models for D2T generation to a real-world dataset consisting of package leaflets of European medicines. We show that fine-tuned transformers are able to generate realistic, multisentence text from data in the biomedical domain, yet have important limitations. We also release a new dataset (BioLeaflets) for benchmarking D2T generation models in the biomedical domain.
Keywords
Cite
@article{arxiv.2109.01518,
title = {Biomedical Data-to-Text Generation via Fine-Tuning Transformers},
author = {Ruslan Yermakov and Nicholas Drago and Angelo Ziletti},
journal= {arXiv preprint arXiv:2109.01518},
year = {2021}
}
Comments
Accepted at ACL-INGL2021 (International Conference on Natural Language Generation organised by the Association for Computational Linguistics)