arXivDaily arXiv每日学术速递 周一至周五更新
北美退伍军人节(Veterans Day),12 日无更新
arXiv 1908.11536cs.CL
收藏

从临床会话中学习推断实体、属性及其关系

Learning to Infer Entities, Properties and their Relations from Clinical Conversations

Google Inc.(谷歌公司)

Nan Du, Mingqiu Wang, Linh Tran, Gang Li, Izhak Shafran

摘要:

最近,我们提出了跨度属性标记(SAT)模型(Du等人,2019)来推断临床实体(例如,症状)及其性质(例如,持续时间)。它解决了大的标签空间和有限的训练数据的挑战,使用分层的两阶段的方法,确定感兴趣的跨度在标记步骤和分配标签的跨度在分类步骤。我们扩展了SAT模型,不仅可以共同推断实体及其属性,还可以推断它们之间的关系。大多数关系抽取模型限制在几个相邻句子内推断标记之间的关系,主要是为了避免高计算复杂性。相比之下,我们提出的R-SAT(R-SAT)模型计算效率高,可以推断整个对话中的关系,平均持续时间为10分钟。我们评估我们的模型上的语料库的临床对话。当给出实体时,R-SAT在识别症状及其属性之间的关系方面优于基线约32%(0.82 vs 0.62 F分数),在药物及其属性方面优于基线约50%(0.60 vs 0.41 F分数)。在联合推断实体和关系这一更困难的任务上,R-SAT模型在症状和药物方面的表现分别为0.34和0.45,显著优于基线模型的0.18和0.35。使用消融分析来量化模型的不同组件的贡献。

英文摘要:

Recently we proposed the Span Attribute Tagging (SAT) Model (Du et al., 2019) to infer clinical entities (e.g., symptoms) and their properties (e.g., duration). It tackles the challenge of large label space and limited training data using a hierarchical two-stage approach that identifies the span of interest in a tagging step and assigns labels to the span in a classification step. We extend the SAT model to jointly infer not only entities and their properties but also relations between them. Most relation extraction models restrict inferring relations between tokens within a few neighboring sentences, mainly to avoid high computational complexity. In contrast, our proposed Relation-SAT (R-SAT) model is computationally efficient and can infer relations over the entire conversation, spanning an average duration of 10 minutes. We evaluate our model on a corpus of clinical conversations. When the entities are given, the R-SAT outperforms baselines in identifying relations between symptoms and their properties by about 32% (0.82 vs 0.62 F-score) and by about 50% (0.60 vs 0.41 F-score) on medications and their properties. On the more difficult task of jointly inferring entities and relations, the R-SAT model achieves a performance of 0.34 and 0.45 for symptoms and medications respectively, which is significantly better than 0.18 and 0.35 for the baseline model. The contributions of different components of the model are quantified using ablation analysis.

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。

↑