Composition-driven symptom phrase recognition for Chinese medical consultation corpora

doi:10.1186/s12911-021-01716-2

CASIA OpenIR > 多模态人工智能系统全国重点实验室 > 人工智能与机器学习（杨雪冰）-技术团队

	Composition-driven symptom phrase recognition for Chinese medical consultation corpora
	Gu,Xuan 1,2; Sun,Zhengya1,2 ; Zhang,Wensheng1,2
发表期刊	BMC Medical Informatics and Decision Making
	2021-12-27
卷号	21 期号:1
通讯作者	Sun,Zhengya(zhengya.sun@ia.ac.cn)
摘要	AbstractBackgroundSymptom phrase recognition is essential to improve the use of unstructured medical consultation corpora for the development of automated question answering systems. A majority of previous works typically require enough manually annotated training data or as complete a symptom dictionary as possible. However, when applied to real scenarios, they will face a dilemma due to the scarcity of the annotated textual resources and the diversity of the spoken language expressions.MethodsIn this paper, we propose a composition-driven method to recognize the symptom phrases from Chinese medical consultation corpora without any annotations. The basic idea is to directly learn models that capture the composition, i.e., the arrangement of the symptom components (semantic units of words). We introduce an automatic annotation strategy for the standard symptom phrases which are collected from multiple data sources. In particular, we combine the position information and the interaction scores between symptom components to characterize the symptom phrases. Equipped with such models, we are allowed to robustly extract symptom phrases that are not seen before.ResultsWithout any manual annotations, our method achieves strong positive results on symptom phrase recognition tasks. Experiments also show that our method enjoys great potential with access to plenty of corpora.ConclusionsCompositionality offers a feasible solution for extracting information from unstructured free text with scarce labels.
关键词	Symptom phrase recognition Named entity recognition Medical consultation Composition driven
DOI	10.1186/s12911-021-01716-2
语种	英语
WOS记录号	BMC:10.1186/s12911-021-01716-2
出版者	BioMed Central
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/46758
专题	多模态人工智能系统全国重点实验室_人工智能与机器学习（杨雪冰）-技术团队
通讯作者	Sun,Zhengya
作者单位	1.University of Chinese Academy of Sciences 2.Chinese Academy of Sciences; Institute of Automation
推荐引用方式 GB/T 7714	Gu,Xuan,Sun,Zhengya,Zhang,Wensheng. Composition-driven symptom phrase recognition for Chinese medical consultation corpora[J]. BMC Medical Informatics and Decision Making,2021,21(1).
APA	Gu,Xuan,Sun,Zhengya,&Zhang,Wensheng.(2021).Composition-driven symptom phrase recognition for Chinese medical consultation corpora.BMC Medical Informatics and Decision Making,21(1).
MLA	Gu,Xuan,et al."Composition-driven symptom phrase recognition for Chinese medical consultation corpora".BMC Medical Informatics and Decision Making 21.1(2021).