e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation

Aaron Nicolson, Jinghui Liu, Jason Dowling, Anthony Nguyen, Bevan Koopman


Abstract
The core novelty of our approach lies in the addition of entropy regularisation to self-critical sequence training. This helps maintain a higher entropy in the token distribution, preventing overfitting to common phrases and ensuring a broader exploration of the vocabulary during training, which is essential for handling the diversity of the radiology reports in the RRG24 datasets. We apply this to a multimodal language model with RadGraph as the reward. Additionally, our model incorporates several other aspects. We use token type embeddings to differentiate between findings and impression section tokens, as well as image embeddings. To handle missing sections, we employ special tokens. We also utilise an attention mask with non-causal masking for the image embeddings and a causal mask for the report token embeddings.
Anthology ID:
2024.bionlp-1.8
Volume:
Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
Month:
August
Year:
2024
Address:
Bangkok, Thailand
Editors:
Dina Demner-Fushman, Sophia Ananiadou, Makoto Miwa, Kirk Roberts, Junichi Tsujii
Venues:
BioNLP | WS
SIG:
SIGBIOMED
Publisher:
Association for Computational Linguistics
Note:
Pages:
99–104
Language:
URL:
https://aclanthology.org/2024.bionlp-1.8
DOI:
10.18653/v1/2024.bionlp-1.8
Bibkey:
Cite (ACL):
Aaron Nicolson, Jinghui Liu, Jason Dowling, Anthony Nguyen, and Bevan Koopman. 2024. e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation. In Proceedings of the 23rd Workshop on Biomedical Natural Language Processing, pages 99–104, Bangkok, Thailand. Association for Computational Linguistics.
Cite (Informal):
e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation (Nicolson et al., BioNLP-WS 2024)
Copy Citation:
PDF:
https://aclanthology.org/2024.bionlp-1.8.pdf