arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2112.09288cs.CLcs.AI
收藏

生物句间关系抽取的神经网络结构

Neural Architectures for Biological Inter-Sentence Relation Extraction

The University of Arizona(亚利桑那大学)

Enrique Noriega-Atala, Peter M. Lovett, Clayton T. Morrison, Mihai Surdeanu

摘要:

我们介绍了一系列用于句间关系抽取的深度学习架构,即,参与者不一定在同一个句子中。我们将这些架构应用于生物医学领域的一个重要用例:将生物背景分配给生化事件。在这项工作中,生物背景被定义为生物系统的类型,其中观察到的生化事件。神经架构编码和聚合相同候选上下文提及的多次出现,以确定它是否是特定事件提及的正确上下文。我们提出了两种广泛类型的架构:第一种类型聚合多个实例,对应于相同的候选上下文相对于事件提及之前发出的分类;第二种类型独立分类每个实例,并使用结果来投票的最终类,类似于集成的方法。我们的实验表明,所提出的神经分类器具有竞争力,其中一些分类器在不需要特征工程的情况下,比之前最先进的传统机器学习方法获得了更好的性能。我们的分析表明,与传统的机器学习分类器相比,神经方法特别提高了精度,并且还演示了句间关系抽取的难度如何随着事件和上下文提及之间的距离增加而增加。

英文摘要:

We introduce a family of deep-learning architectures for inter-sentence relation extraction, i.e., relations where the participants are not necessarily in the same sentence. We apply these architectures to an important use case in the biomedical domain: assigning biological context to biochemical events. In this work, biological context is defined as the type of biological system within which the biochemical event is observed. The neural architectures encode and aggregate multiple occurrences of the same candidate context mentions to determine whether it is the correct context for a particular event mention. We propose two broad types of architectures: the first type aggregates multiple instances that correspond to the same candidate context with respect to event mention before emitting a classification; the second type independently classifies each instance and uses the results to vote for the final class, akin to an ensemble approach. Our experiments show that the proposed neural classifiers are competitive and some achieve better performance than previous state of the art traditional machine learning methods without the need for feature engineering. Our analysis shows that the neural methods particularly improve precision compared to traditional machine learning classifiers and also demonstrates how the difficulty of inter-sentence relation extraction increases as the distance between the event and context mentions increase.

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。

↑