@inproceedings{rohanian-etal-2023-using,
title = "Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints",
author = "Rohanian, Omid and
Jauncey, Hannah and
Nouriborji, Mohammadmahdi and
Kumar, Vinod and
Gonalves, Bronner P. and
Kartsonaki, Christiana and
Clinical Characterisation Group, Isaric and
Merson, Laura and
Clifton, David",
editor = "Demner-fushman, Dina and
Ananiadou, Sophia and
Cohen, Kevin",
booktitle = "The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks",
month = jul,
year = "2023",
address = "Toronto, Canada",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.bionlp-1.5",
doi = "10.18653/v1/2023.bionlp-1.5",
pages = "62--78",
abstract = "Processing information locked within clinical health records is a challenging task that remains an active area of research in biomedical NLP. In this work, we evaluate a broad set of machine learning techniques ranging from simple RNNs to specialised transformers such as BioBERT on a dataset containing clinical notes along with a set of annotations indicating whether a sample is cancer-related or not. Furthermore, we specifically employ efficient fine-tuning methods from NLP, namely, bottleneck adapters and prompt tuning, to adapt the models to our specialised task. Our evaluations suggest that fine-tuning a frozen BERT model pre-trained on natural language and with bottleneck adapters outperforms all other strategies, including full fine-tuning of the specialised BioBERT model. Based on our findings, we suggest that using bottleneck adapters in low-resource situations with limited access to labelled data or processing capacity could be a viable strategy in biomedical text mining.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="rohanian-etal-2023-using">
<titleInfo>
<title>Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints</title>
</titleInfo>
<name type="personal">
<namePart type="given">Omid</namePart>
<namePart type="family">Rohanian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hannah</namePart>
<namePart type="family">Jauncey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammadmahdi</namePart>
<namePart type="family">Nouriborji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vinod</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bronner</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Gonalves</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christiana</namePart>
<namePart type="family">Kartsonaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Isaric</namePart>
<namePart type="family">Clinical Characterisation Group</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Laura</namePart>
<namePart type="family">Merson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Clifton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks</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">Kevin</namePart>
<namePart type="family">Cohen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Toronto, Canada</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Processing information locked within clinical health records is a challenging task that remains an active area of research in biomedical NLP. In this work, we evaluate a broad set of machine learning techniques ranging from simple RNNs to specialised transformers such as BioBERT on a dataset containing clinical notes along with a set of annotations indicating whether a sample is cancer-related or not. Furthermore, we specifically employ efficient fine-tuning methods from NLP, namely, bottleneck adapters and prompt tuning, to adapt the models to our specialised task. Our evaluations suggest that fine-tuning a frozen BERT model pre-trained on natural language and with bottleneck adapters outperforms all other strategies, including full fine-tuning of the specialised BioBERT model. Based on our findings, we suggest that using bottleneck adapters in low-resource situations with limited access to labelled data or processing capacity could be a viable strategy in biomedical text mining.</abstract>
<identifier type="citekey">rohanian-etal-2023-using</identifier>
<identifier type="doi">10.18653/v1/2023.bionlp-1.5</identifier>
<location>
<url>https://aclanthology.org/2023.bionlp-1.5</url>
</location>
<part>
<date>2023-07</date>
<extent unit="page">
<start>62</start>
<end>78</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints
%A Rohanian, Omid
%A Jauncey, Hannah
%A Nouriborji, Mohammadmahdi
%A Kumar, Vinod
%A Gonalves, Bronner P.
%A Kartsonaki, Christiana
%A Clinical Characterisation Group, Isaric
%A Merson, Laura
%A Clifton, David
%Y Demner-fushman, Dina
%Y Ananiadou, Sophia
%Y Cohen, Kevin
%S The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks
%D 2023
%8 July
%I Association for Computational Linguistics
%C Toronto, Canada
%F rohanian-etal-2023-using
%X Processing information locked within clinical health records is a challenging task that remains an active area of research in biomedical NLP. In this work, we evaluate a broad set of machine learning techniques ranging from simple RNNs to specialised transformers such as BioBERT on a dataset containing clinical notes along with a set of annotations indicating whether a sample is cancer-related or not. Furthermore, we specifically employ efficient fine-tuning methods from NLP, namely, bottleneck adapters and prompt tuning, to adapt the models to our specialised task. Our evaluations suggest that fine-tuning a frozen BERT model pre-trained on natural language and with bottleneck adapters outperforms all other strategies, including full fine-tuning of the specialised BioBERT model. Based on our findings, we suggest that using bottleneck adapters in low-resource situations with limited access to labelled data or processing capacity could be a viable strategy in biomedical text mining.
%R 10.18653/v1/2023.bionlp-1.5
%U https://aclanthology.org/2023.bionlp-1.5
%U https://doi.org/10.18653/v1/2023.bionlp-1.5
%P 62-78
Markdown (Informal)
[Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints](https://aclanthology.org/2023.bionlp-1.5) (Rohanian et al., BioNLP 2023)
ACL
- Omid Rohanian, Hannah Jauncey, Mohammadmahdi Nouriborji, Vinod Kumar, Bronner P. Gonalves, Christiana Kartsonaki, Isaric Clinical Characterisation Group, Laura Merson, and David Clifton. 2023. Using Bottleneck Adapters to Identify Cancer in Clinical Notes under Low-Resource Constraints. In The 22nd Workshop on Biomedical Natural Language Processing and BioNLP Shared Tasks, pages 62–78, Toronto, Canada. Association for Computational Linguistics.