{"title":"用于放射学报告生成的Token不平衡适应","authors":"Yuexin Wu, I. Huang, Xiaolei Huang","doi":"10.48550/arXiv.2304.09185","DOIUrl":null,"url":null,"abstract":"Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of radiology report generators, as complex medical terms appear less frequently but reflect more medical information. In this study, we demonstrate how current state-of-the-art models fail to generate infrequent tokens on two standard benchmark datasets (IU X-RAY and MIMIC-CXR) of radiology report generation. % However, no prior study has proposed methods to adapt infrequent tokens for text generators feeding with medical images. To solve the challenge, we propose the \\textbf{T}oken \\textbf{Im}balance Adapt\\textbf{er} (\\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation.","PeriodicalId":87342,"journal":{"name":"Proceedings of the ACM Conference on Health, Inference, and Learning","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2023-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Token Imbalance Adaptation for Radiology Report Generation\",\"authors\":\"Yuexin Wu, I. Huang, Xiaolei Huang\",\"doi\":\"10.48550/arXiv.2304.09185\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of radiology report generators, as complex medical terms appear less frequently but reflect more medical information. In this study, we demonstrate how current state-of-the-art models fail to generate infrequent tokens on two standard benchmark datasets (IU X-RAY and MIMIC-CXR) of radiology report generation. % However, no prior study has proposed methods to adapt infrequent tokens for text generators feeding with medical images. To solve the challenge, we propose the \\\\textbf{T}oken \\\\textbf{Im}balance Adapt\\\\textbf{er} (\\\\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation.\",\"PeriodicalId\":87342,\"journal\":{\"name\":\"Proceedings of the ACM Conference on Health, Inference, and Learning\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-18\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the ACM Conference on Health, Inference, and Learning\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.48550/arXiv.2304.09185\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the ACM Conference on Health, Inference, and Learning","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.48550/arXiv.2304.09185","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0
摘要
文本文档中自然存在不平衡的标记分布,导致神经语言模型在频繁标记上过拟合。代币失衡可能会抑制放射学报告生成器的稳健性,因为复杂的医学术语出现的频率较低,但反映了更多的医学信息。在本研究中,我们展示了当前最先进的模型如何无法在两个标准基准数据集(IU X-RAY和MIMIC-CXR)上生成罕见的令牌。 % However, no prior study has proposed methods to adapt infrequent tokens for text generators feeding with medical images. To solve the challenge, we propose the \textbf{T}oken \textbf{Im}balance Adapt\textbf{er} (\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation.
Token Imbalance Adaptation for Radiology Report Generation
Imbalanced token distributions naturally exist in text documents, leading neural language models to overfit on frequent tokens. The token imbalance may dampen the robustness of radiology report generators, as complex medical terms appear less frequently but reflect more medical information. In this study, we demonstrate how current state-of-the-art models fail to generate infrequent tokens on two standard benchmark datasets (IU X-RAY and MIMIC-CXR) of radiology report generation. % However, no prior study has proposed methods to adapt infrequent tokens for text generators feeding with medical images. To solve the challenge, we propose the \textbf{T}oken \textbf{Im}balance Adapt\textbf{er} (\textit{TIMER}), aiming to improve generation robustness on infrequent tokens. The model automatically leverages token imbalance by an unlikelihood loss and dynamically optimizes generation processes to augment infrequent tokens. We compare our approach with multiple state-of-the-art methods on the two benchmarks. Experiments demonstrate the effectiveness of our approach in enhancing model robustness overall and infrequent tokens. Our ablation analysis shows that our reinforcement learning method has a major effect in adapting token imbalance for radiology report generation.