MedCOD:使用丰富的字典链框架改进大型语言模型的英语到西班牙语医学翻译
Md Shahidul Salim1,2, Lian Fu3, Arav Adikesh Ramakrishnan3
1Center for Healthcare Organization and Implementation Research, VA Bedford Health Care.
概括
我们开发了MedCOD,这是一个框架,通过将结构化的医学知识整合到大型语言模型 (LLM) 中来增强英语到西班牙语的医学翻译. 这种方法显著提高了各种模型的翻译质量.
科学领域:
- 医疗信息学 医疗信息学
- 自然语言处理自然语言处理.
- 计算语言学 计算语言学
背景情况:
- 准确的医学翻译对于全球医疗保健的准入至关重要.
- 大型语言模型 (LLM) 是有前途的,但在特定领域的医学术语方面存在困难.
- 现有的翻译方法缺乏对结构化医学知识的强有力的整合.
研究的目的:
- 引入MedCOD (医学字典链),这是一个新的混合框架,用于改进英语到西班牙语的医学翻译.
- 通过整合UMLS和LLM-KB范式的结构化领域知识来增强LLM.
- 评估MedCOD在提高多个开源LLMs的翻译质量的有效性.
主要方法:
- 构建了2999个英语-西班牙语MedlinePlus文章的并行库.
- 开发了一套具有结构化的医疗背景的100句话测试集.
- 采用结构化提示,多语言变体,同义词和UMLS定义.
- 在四个开源LLM (Phi-4,Qwen2.5-14B,Qwen2.5-7B,LLaMA-3.1-8B) 上使用了基于LoRA的微调.
主要成果:
- 在所有评估的LLMs中,MedCOD显著提高了翻译质量.
- 使用MedCOD和微调的Phi-4获得了优异的BLEU (44.23),chrF++ (28.91) 和COMET (0.863) 分数.
- 无论是MedCOD提示还是模型调整,都独立地提高了性能,联合使用带来了最大的收益.
- 性能超过了强大的基线模型,如GPT-4o和GPT-4o-mini.
结论:
- 通过MedCOD进行结构化的知识整合,大大提高了医学翻译的LLM性能.
- MedCOD框架提供了一种可行的策略,可以提高医学语言翻译的准确性和可靠性.
- 这种方法对推进全球卫生沟通中人工智能应用具有重大潜力.
相关概念视频
Termination of Translation
27.8K
The large ribosomal subunit has several important structures essential to translation. These include the peptidyl transferase center (PTC) - which is the site where the peptide bond is formed - and a large, internal, water-filled tube through which the nascent polypeptide moves. This latter structure is called the Peptide Exit Tunnel, and it begins at the PTC and spans the body of the large ribosomal subunit. During translation, as the nascent polypeptide chain is synthesized, it passes through...
27.8K
Improving Translational Accuracy
15.0K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
15.0K
Language
919
Language is a unique communication system that uses words and systematic rules to organize and transmit information. Unlike other forms of communication, which may involve postures, movements, odors, or vocalizations, language relies on symbols and grammar. This makes human communication distinct from that of other species, who also communicate but do not use language in the same way humans do.
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
Corballis and Suddendorf (2007) and Tomasello and Rakoczy (2003) highlight the role of language in...
919
Translation
157.1K
Lesson: Translation
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of...
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of...
157.1K
Translation
17.9K
Translation is the process of synthesizing proteins from the genetic information carried by messenger RNA (mRNA). Following transcription, it constitutes the final step in the expression of genes. This process is carried out by ribosomes, complexes of protein and specialized RNA molecules. Ribosomes, transfer RNA (tRNA), and other proteins produce a chain of amino acids—the polypeptide—as the end product of translation.
Translation Produces the Building Blocks of Life
Proteins are...
Translation Produces the Building Blocks of Life
Proteins are...
17.9K
Initiation of Translation
39.1K
Initiating translation is complex because it involves multiple molecules. Initiator tRNA, ribosomal subunits, and eukaryotic initiation factors (eIFs) are all required to assemble on the initiation codon of mRNA. This process consists of several steps that are mediated by different eIFs.
First, the initiator tRNA must be selected from the pool of elongator tRNAs by eukaryotic initiation factor 2 (eIF2). The initiator tRNA (Met-tRNAi) has conserved sequence elements including modified bases at...
First, the initiator tRNA must be selected from the pool of elongator tRNAs by eukaryotic initiation factor 2 (eIF2). The initiator tRNA (Met-tRNAi) has conserved sequence elements including modified bases at...
39.1K


