查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Translation is the subject of a report. According to news reporting out of Evanston, Illinois, by NewsRx editors, research stated, “Medical texts present significant domain-s pecific challenges, and manually curating these texts is a time-consuming and la bor-intensive process. To address this, natural language processing (NLP) algori thms have been developed to automate text processing.” Our news journalists obtained a quote from the research from Northwestern Univer sity, “In the biomedical field, various toolkits for text processing exist, whic h have greatly improved the efficiency of handling unstructured text. However, t hese existing toolkits tend to emphasize different perspectives, and none of the m offer generation capabilities, leaving a significant gap in the current offeri ngs. This study aims to describe the development and preliminary evaluation of A scle. Ascle is tailored for biomedical researchers and clinical staff with an ea sy-to-use, all-in-one solution that requires minimal programming expertise. For the first time, Ascle provides 4 advanced and challenging generative functions: question-answering, text summarization, text simplification, and machine transla tion. In addition, Ascle integrates 12 essential NLP functions, along with query and search capabilities for clinical databases. We fine-tuned 32 domainspecifi c language models and evaluated them thoroughly on 27 established benchmarks. In addition, for the question-answering task, we developed a retrieval-augmented g eneration (RAG) framework for large language models that incorporated a medical knowledge graph with ranking techniques to enhance the reliability of generated answers. Additionally, we conducted a physician validation to assess the quality of generated content beyond automated metrics. The fine-tuned models and RAG fr amework consistently enhanced text generation tasks. For example, the fine-tuned models improved the machine translation task by 20.27 in terms of BLEU score. I n the question-answering task, the RAG framework raised the ROUGE-L score by 18% over the vanilla models. Physician validation of generated answers showed high s cores for readability (4.95/5) and relevancy (4.43/5), with a lower score for ac curacy (3.90/5) and completeness (3.31/5). This study introduces the development and evaluation of Ascle, a user-friendly NLP toolkit designed for medical text generation. All code is publicly available through the Ascle GitHub repository.”
NETL
NSTL