arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2109.03570cs.CL
收藏

西班牙语的生物医学和临床语言模型:在中等资源场景中特定领域预训练的好处

Biomedical and Clinical Language Models for Spanish: On the Benefits of Domain-Specific Pretraining in a Mid-Resource Scenario

Text Mining Unit Barcelona Supercomputing Center(文本挖掘组 巴塞罗那超级计算中心)

Casimiro Pio Carrino, Jordi Armengol-Estapé, Asier Gutiérrez-Fandiño, Joan Llop-Palao, Marc Pàmies, Aitor Gonzalez-Agirre, Marta Villegas

摘要:

这项工作提出了西班牙语的生物医学和临床语言模型,通过实验不同的预训练选择,如在单词和子单词级掩蔽,不同的词汇量和测试域数据,寻找更好的语言表示。有趣的是,在没有足够的临床数据从头开始训练模型的情况下,我们应用混合域预训练和跨域转移方法来生成适合真实世界临床数据的高性能生物临床模型。我们评估了我们的模型上的命名实体识别(NER)任务的生物医学文件和具有挑战性的出院报告。当与具有竞争力的mBERT和BETO模型相比时,我们在所有NER任务中的表现都明显优于它们。最后,我们通过提供一个有趣的以词汇为中心的分析,研究了模型的词汇对NER性能的影响。结果证实,特定领域的预训练是在下游NER任务中实现更高性能的基础,即使在中间资源的情况下。据我们所知,我们为西班牙语提供了第一个基于生物医学和临床转换器的预训练语言模型,旨在促进西班牙语NLP在生物医学中的应用。我们最好的模型可以在HuggingFace中心免费获得:https://huggingface.co/BSC-TeMU。

英文摘要:

This work presents biomedical and clinical language models for Spanish by experimenting with different pretraining choices, such as masking at word and subword level, varying the vocabulary size and testing with domain data, looking for better language representations. Interestingly, in the absence of enough clinical data to train a model from scratch, we applied mixed-domain pretraining and cross-domain transfer approaches to generate a performant bio-clinical model suitable for real-world clinical data. We evaluated our models on Named Entity Recognition (NER) tasks for biomedical documents and challenging hospital discharge reports. When compared against the competitive mBERT and BETO models, we outperform them in all NER tasks by a significant margin. Finally, we studied the impact of the model's vocabulary on the NER performances by offering an interesting vocabulary-centric analysis. The results confirm that domain-specific pretraining is fundamental to achieving higher performances in downstream NER tasks, even within a mid-resource scenario. To the best of our knowledge, we provide the first biomedical and clinical transformer-based pretrained language models for Spanish, intending to boost native Spanish NLP applications in biomedicine. Our best models are freely available in the HuggingFace hub: https://huggingface.co/BSC-TeMU.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑