@inproceedings{nicolson-etal-2024-e,
title = "e-Health {CSIRO} at {RRG}24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation",
author = "Nicolson, Aaron and
Liu, Jinghui and
Dowling, Jason and
Nguyen, Anthony and
Koopman, Bevan",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Miwa, Makoto and
Roberts, Kirk and
Tsujii, Junichi",
booktitle = "Proceedings of the 23rd Workshop on Biomedical Natural Language Processing",
month = aug,
year = "2024",
address = "Bangkok, Thailand",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.bionlp-1.8",
pages = "99--104",
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.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nicolson-etal-2024-e">
<titleInfo>
<title>e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aaron</namePart>
<namePart type="family">Nicolson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghui</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jason</namePart>
<namePart type="family">Dowling</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anthony</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bevan</namePart>
<namePart type="family">Koopman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 23rd Workshop on Biomedical Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Makoto</namePart>
<namePart type="family">Miwa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kirk</namePart>
<namePart type="family">Roberts</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junichi</namePart>
<namePart type="family">Tsujii</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<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.</abstract>
<identifier type="citekey">nicolson-etal-2024-e</identifier>
<location>
<url>https://aclanthology.org/2024.bionlp-1.8</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>99</start>
<end>104</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation
%A Nicolson, Aaron
%A Liu, Jinghui
%A Dowling, Jason
%A Nguyen, Anthony
%A Koopman, Bevan
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Miwa, Makoto
%Y Roberts, Kirk
%Y Tsujii, Junichi
%S Proceedings of the 23rd Workshop on Biomedical Natural Language Processing
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand
%F nicolson-etal-2024-e
%X 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.
%U https://aclanthology.org/2024.bionlp-1.8
%P 99-104
Markdown (Informal)
[e-Health CSIRO at RRG24: Entropy-Augmented Self-Critical Sequence Training for Radiology Report Generation](https://aclanthology.org/2024.bionlp-1.8) (Nicolson et al., BioNLP-WS 2024)
ACL