Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ...
Deep learning approaches exhibit promising performances on various text tasks. However, they are still struggling on medical text classification since samples are often extremely imbalanced and scarce. Different from existing mainstream approaches that focus on supplementary semantics with external...
Main Authors: | , , , , , , |
---|---|
Format: | Report |
Language: | unknown |
Published: |
arXiv
2023
|
Subjects: | |
Online Access: | https://dx.doi.org/10.48550/arxiv.2311.16650 https://arxiv.org/abs/2311.16650 |
id |
ftdatacite:10.48550/arxiv.2311.16650 |
---|---|
record_format |
openpolar |
spelling |
ftdatacite:10.48550/arxiv.2311.16650 2023-12-31T10:06:17+01:00 Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... Yan, Jiahuan Gao, Haojun Kai, Zhang Liu, Weize Chen, Danny Wu, Jian Chen, Jintai 2023 https://dx.doi.org/10.48550/arxiv.2311.16650 https://arxiv.org/abs/2311.16650 unknown arXiv arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ Computation and Language cs.CL FOS Computer and information sciences CreativeWork Preprint article Article 2023 ftdatacite https://doi.org/10.48550/arxiv.2311.16650 2023-12-01T12:19:45Z Deep learning approaches exhibit promising performances on various text tasks. However, they are still struggling on medical text classification since samples are often extremely imbalanced and scarce. Different from existing mainstream approaches that focus on supplementary semantics with external medical information, this paper aims to rethink the data challenges in medical texts and present a novel framework-agnostic algorithm called Text2Tree that only utilizes internal label hierarchy in training deep learning models. We embed the ICD code tree structure of labels into cascade attention modules for learning hierarchy-aware label representations. Two new learning schemes, Similarity Surrogate Learning (SSL) and Dissimilarity Mixup Learning (DML), are devised to boost text classification by reusing and distinguishing samples of other labels following the label representation hierarchy, respectively. Experiments on authoritative public datasets and real-world medical records show that our approach stably ... : EMNLP 2023 Findings. Code: https://github.com/jyansir/Text2Tree ... Report DML DataCite Metadata Store (German National Library of Science and Technology) |
institution |
Open Polar |
collection |
DataCite Metadata Store (German National Library of Science and Technology) |
op_collection_id |
ftdatacite |
language |
unknown |
topic |
Computation and Language cs.CL FOS Computer and information sciences |
spellingShingle |
Computation and Language cs.CL FOS Computer and information sciences Yan, Jiahuan Gao, Haojun Kai, Zhang Liu, Weize Chen, Danny Wu, Jian Chen, Jintai Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... |
topic_facet |
Computation and Language cs.CL FOS Computer and information sciences |
description |
Deep learning approaches exhibit promising performances on various text tasks. However, they are still struggling on medical text classification since samples are often extremely imbalanced and scarce. Different from existing mainstream approaches that focus on supplementary semantics with external medical information, this paper aims to rethink the data challenges in medical texts and present a novel framework-agnostic algorithm called Text2Tree that only utilizes internal label hierarchy in training deep learning models. We embed the ICD code tree structure of labels into cascade attention modules for learning hierarchy-aware label representations. Two new learning schemes, Similarity Surrogate Learning (SSL) and Dissimilarity Mixup Learning (DML), are devised to boost text classification by reusing and distinguishing samples of other labels following the label representation hierarchy, respectively. Experiments on authoritative public datasets and real-world medical records show that our approach stably ... : EMNLP 2023 Findings. Code: https://github.com/jyansir/Text2Tree ... |
format |
Report |
author |
Yan, Jiahuan Gao, Haojun Kai, Zhang Liu, Weize Chen, Danny Wu, Jian Chen, Jintai |
author_facet |
Yan, Jiahuan Gao, Haojun Kai, Zhang Liu, Weize Chen, Danny Wu, Jian Chen, Jintai |
author_sort |
Yan, Jiahuan |
title |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... |
title_short |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... |
title_full |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... |
title_fullStr |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... |
title_full_unstemmed |
Text2Tree: Aligning Text Representation to the Label Tree Hierarchy for Imbalanced Medical Classification ... |
title_sort |
text2tree: aligning text representation to the label tree hierarchy for imbalanced medical classification ... |
publisher |
arXiv |
publishDate |
2023 |
url |
https://dx.doi.org/10.48550/arxiv.2311.16650 https://arxiv.org/abs/2311.16650 |
genre |
DML |
genre_facet |
DML |
op_rights |
arXiv.org perpetual, non-exclusive license http://arxiv.org/licenses/nonexclusive-distrib/1.0/ |
op_doi |
https://doi.org/10.48550/arxiv.2311.16650 |
_version_ |
1786838273367212032 |