arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1909.03044cs.CLcs.LGstat.ML
收藏

使用在生物医学语料库上预训练的句子嵌入的深度学习提高了在电子医疗记录中查找相似句子的性能

Deep learning with sentence embeddings pre-trained on biomedical corpora improves the performance of finding similar sentences in electronic medical records

National Center for Biotechnology Information, National Library of Medicine, National Institutes of Health(美国国立卫生研究院国家医学图书馆国家生物技术信息中心)

Qingyu Chen, Jingcheng Du, Sun Kim, W. John Wilbur, Zhiyong Lu

摘要:

句子语义的获取在文本挖掘应用中起着至关重要的作用。尽管在一般领域的相关数据集和模型的开发不断努力,但数据集和模型在生物医学和临床领域都是有限的。BioCreative/OHNLP组织者首次尝试从临床笔记中注释1,068个句子对,并呼吁社区努力解决语义文本相似性(BioCreative/OHNLP STS)挑战。我们使用传统的机器学习和深度学习方法开发模型。对于后期挑战,我们关注两个模型:随机森林和编码器网络。我们应用了在PubMed摘要和MIMIC-III临床笔记上预训练的句子嵌入,并相应地更新了随机森林和编码器网络。官方结果表明,我们最好的提交是八个模型的集合。它达到了0.8328的人相关系数,在来自4个团队的13个提交中表现最好。对于挑战后,随机森林和编码器网络的性能都得到了提高;特别是,编码器网络的相关性提高了约13%。在挑战任务期间,没有端到端的深度学习模型比采用手动制作的功能的机器学习模型具有更好的性能。相比之下,使用在生物医学语料库上预训练的句子嵌入,编码器网络现在实现了~0.84的相关性,高于最初的最佳模型。采用改进版本的随机森林和编码器网络作为输入的集成模型进一步将性能提高到0.8528。具有在生物医学语料库上预训练的句子嵌入的深度学习模型在测试集上实现了最高的性能。

英文摘要:

Capturing sentence semantics plays a vital role in a range of text mining applications. Despite continuous efforts on the development of related datasets and models in the general domain, both datasets and models are limited in biomedical and clinical domains. The BioCreative/OHNLP organizers have made the first attempt to annotate 1,068 sentence pairs from clinical notes and have called for a community effort to tackle the Semantic Textual Similarity (BioCreative/OHNLP STS) challenge. We developed models using traditional machine learning and deep learning approaches. For the post challenge, we focus on two models: the Random Forest and the Encoder Network. We applied sentence embeddings pre-trained on PubMed abstracts and MIMIC-III clinical notes and updated the Random Forest and the Encoder Network accordingly. The official results demonstrated our best submission was the ensemble of eight models. It achieved a Person correlation coefficient of 0.8328, the highest performance among 13 submissions from 4 teams. For the post challenge, the performance of both Random Forest and the Encoder Network was improved; in particular, the correlation of the Encoder Network was improved by ~13%. During the challenge task, no end-to-end deep learning models had better performance than machine learning models that take manually-crafted features. In contrast, with the sentence embeddings pre-trained on biomedical corpora, the Encoder Network now achieves a correlation of ~0.84, which is higher than the original best model. The ensembled model taking the improved versions of the Random Forest and Encoder Network as inputs further increased performance to 0.8528. Deep learning models with sentence embeddings pre-trained on biomedical corpora achieve the highest performance on the test set.

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。

↑