Infusing clinical knowledge into tokenisers for language models

• Published in: arXiv.org
• Main Authors: Hasan, Abul, Wu, Jinge, Nguyen, Quang Ngoc, Salomé Andres, Guellil, Imane, Zhang, Huayu, Casey, Arlene, Alex, Beatrice, Guthrie, Bruce, Wu, Honghan
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 20.06.2024
• Subjects: Automation; Coding; Language; Representations; Semantics
• ISSN: 2331-8422

This study introduces a novel knowledge enhanced tokenisation mechanism, K-Tokeniser, for clinical text processing. Technically, at initialisation stage, K-Tokeniser populates global representations of tokens based on semantic types of domain concepts (such as drugs or diseases) from either a domain ontology like Unified Medical Language System or the training data of the task related corpus. At training or inference stage, sentence level localised context will be utilised for choosing the optimal global token representation to realise the semantic-based tokenisation. To avoid pretraining using the new tokeniser, an embedding initialisation approach is proposed to generate representations for new tokens. Using three transformer-based language models, a comprehensive set of experiments are conducted on four real-world datasets for evaluating K-Tokeniser in a wide range of clinical text analytics tasks including clinical concept and relation extraction, automated clinical coding, clinical phenotype identification, and clinical research article classification. Overall, our models demonstrate consistent improvements over their counterparts in all tasks. In particular, substantial improvements are observed in the automated clinical coding task with 13\% increase on Micro \(F_1\) score. Furthermore, K-Tokeniser also shows significant capacities in facilitating quicker converge of language models. Specifically, using K-Tokeniser, the language models would only require 50\% of the training data to achieve the best performance of the baseline tokeniser using all training data in the concept extraction task and less than 20\% of the data for the automated coding task. It is worth mentioning that all these improvements require no pre-training process, making the approach generalisable.