Specialised or Generic? Tokenization Choices for Radiology Language Models

• URL: http://arxiv.org/abs/2508.09952v1
• Date: Wed, 13 Aug 2025 17:13:56 GMT
• Title: Specialised or Generic? Tokenization Choices for Radiology Language Models
• Authors: Hermione Warr, Wentian Xu, Harry Anthony, Yasin Ibrahim, Daniel McGowan, Konstantinos Kamnitsas,
• Abstract summary: vocabulary used by language models (LM) plays a key role in text generation quality.<n>General, medical, and domain-specific tokenizers on the task of radiology report summarisation across three imaging modalities.<n>Our findings demonstrate that medical and domain-specific vocabularies outperformed widely used natural language alternatives when models are trained from scratch.
• Score: 2.081299660192454
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: The vocabulary used by language models (LM) - defined by the tokenizer - plays a key role in text generation quality. However, its impact remains under-explored in radiology. In this work, we address this gap by systematically comparing general, medical, and domain-specific tokenizers on the task of radiology report summarisation across three imaging modalities. We also investigate scenarios with and without LM pre-training on PubMed abstracts. Our findings demonstrate that medical and domain-specific vocabularies outperformed widely used natural language alternatives when models are trained from scratch. Pre-training partially mitigates performance differences between tokenizers, whilst the domain-specific tokenizers achieve the most favourable results. Domain-specific tokenizers also reduce memory requirements due to smaller vocabularies and shorter sequences. These results demonstrate that adapting the vocabulary of LMs to the clinical domain provides practical benefits, including improved performance and reduced computational demands, making such models more accessible and effective for both research and real-world healthcare settings.

Related papers

• Tokenization and Morphological Fidelity in Uralic NLP: A Cross-Lingual Evaluation [9.23725598061561]
  This study systematically compares three subword paradigms -- Byte Pair.<n>(BPE), Overlap BPE (OBPE), and Unigram Language Model -- across six Uralic languages.<n>We show OBPE consistently achieves stronger morphological alignment and higher tagging accuracy than conventional methods.
  arXiv  Detail & Related papers  (2026-02-04T05:59:25Z)
• Uncertainty-aware Medical Diagnostic Phrase Identification and Grounding [72.18719355481052]
  We introduce a novel task called Medical Report Grounding (MRG)<n>MRG aims to directly identify diagnostic phrases and their corresponding grounding boxes from medical reports in an end-to-end manner.<n>We propose uMedGround, a robust and reliable framework that leverages a multimodal large language model to predict diagnostic phrases.
  arXiv  Detail & Related papers  (2024-04-10T07:41:35Z)
• Comprehensive Study on German Language Models for Clinical and Biomedical Text Understanding [16.220303664681172]
  We pre-trained several German medical language models on 2.4B tokens derived from translated public English medical data and 3B tokens of German clinical data. The resulting models were evaluated on various German downstream tasks, including named entity recognition (NER), multi-label classification, and extractive question answering. We conclude that continuous pre-training has demonstrated the ability to match or even exceed the performance of clinical models trained from scratch.
  arXiv  Detail & Related papers  (2024-04-08T17:24:04Z)
• Enhancing Medical Specialty Assignment to Patients using NLP Techniques [0.0]
  We propose an alternative approach that achieves superior performance while being computationally efficient. Specifically, we utilize keywords to train a deep learning architecture that outperforms a language model pretrained on a large corpus of text. Our results demonstrate that utilizing keywords for text classification significantly improves classification performance.
  arXiv  Detail & Related papers  (2023-12-09T14:13:45Z)
• UMLS-KGI-BERT: Data-Centric Knowledge Integration in Transformers for Biomedical Entity Recognition [3.5555176462255824]
  This work contributes a data-centric paradigm for enriching the language representations of biomedical transformer-encoder LMs by extracting text sequences from the UMLS.<n>Preliminary results from experiments in the extension of pre-trained LMs as well as training from scratch show that this framework improves downstream performance on multiple biomedical and clinical Named Entity Recognition (NER) tasks.
  arXiv  Detail & Related papers  (2023-07-20T18:08:34Z)
• An Iterative Optimizing Framework for Radiology Report Summarization with ChatGPT [80.33783969507458]
  The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians. Recent studies have achieved promising results in automatic impression generation using large-scale medical text data. These models often require substantial amounts of medical text data and have poor generalization performance.
  arXiv  Detail & Related papers  (2023-04-17T17:13:42Z)
• Combining Contrastive Learning and Knowledge Graph Embeddings to develop medical word embeddings for the Italian language [0.0]
  This paper attempts to improve available embeddings in the uncovered niche of the Italian medical domain. The main objective is to improve the accuracy of semantic similarity between medical terms. Since the Italian language lacks medical texts and controlled vocabularies, we have developed a specific solution.
  arXiv  Detail & Related papers  (2022-11-09T17:12:28Z)
• Clinical Named Entity Recognition using Contextualized Token Representations [49.036805795072645]
  This paper introduces the technique of contextualized word embedding to better capture the semantic meaning of each word based on its context. We pre-train two deep contextualized language models, Clinical Embeddings from Language Model (C-ELMo) and Clinical Contextual String Embeddings (C-Flair) Explicit experiments show that our models gain dramatic improvements compared to both static word embeddings and domain-generic language models.
  arXiv  Detail & Related papers  (2021-06-23T18:12:58Z)
• CBLUE: A Chinese Biomedical Language Understanding Evaluation Benchmark [51.38557174322772]
  We present the first Chinese Biomedical Language Understanding Evaluation benchmark. It is a collection of natural language understanding tasks including named entity recognition, information extraction, clinical diagnosis normalization, single-sentence/sentence-pair classification. We report empirical results with the current 11 pre-trained Chinese models, and experimental results show that state-of-the-art neural models perform by far worse than the human ceiling.
  arXiv  Detail & Related papers  (2021-06-15T12:25:30Z)
• Domain-Specific Language Model Pretraining for Biomedical Natural Language Processing [73.37262264915739]
  We show that for domains with abundant unlabeled text, such as biomedicine, pretraining language models from scratch results in substantial gains. Our experiments show that domain-specific pretraining serves as a solid foundation for a wide range of biomedical NLP tasks.
  arXiv  Detail & Related papers  (2020-07-31T00:04:15Z)
• A Comparative Study of Lexical Substitution Approaches based on Neural Language Models [117.96628873753123]
  We present a large-scale comparative study of popular neural language and masked language models. We show that already competitive results achieved by SOTA LMs/MLMs can be further improved if information about the target word is injected properly.
  arXiv  Detail & Related papers  (2020-05-29T18:43:22Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.