Biomedical event trigger detection by dependency-based word embedding.
Biomedical event trigger detection by dependency-based word embedding.
复制标题
通过基于依赖性的词嵌入进行生物医学事件触发检测
DOI：
10.1186/s12920-016-0203-8
复制
发表时间：
2016-08-10
影响因子：
2.7
通讯作者：
Sun Y
中科院分区：
文献类型：
--
作者：
Wang J;Zhang J;An Y;Lin H;Yang Z;Zhang Y;Sun Y
背景在生物医学研究中，揭示实体之间复杂关系的事件起着重要作用。生物医学事件触发点识别在生物医学事件提取中具有重要作用，已成为当前的研究热点。传统的机器学习方法，如支持向量机（SVM）和maxent分类器，其目的是手动设计功能强大的特征馈送到分类器，依赖于对特定任务的理解，不能推广到新的领域或新的例子。我们提出了一种利用基于依赖关系的神经网络模型的方法，基于单词嵌入，自动从原始输入中学习重要特征，用于触发分类。首先，我们使用Word2vec的修改版本Word2vecf，学习基于依赖关系树的具有丰富语义和功能信息的词嵌入。然后使用神经网络架构来学习基于原始依赖性的词嵌入的更重要的特征表示。同时，我们在训练时动态调整嵌入，以适应触发分类任务。最后，softmax分类器标签的例子，通过特定的触发类使用的功能学习的model.ResultsThe实验结果表明，我们的方法实现了一个微观平均F1得分为78.27和一个宏观平均F1得分为76.94%，在显着的触发类，并执行优于基线方法。此外，我们可以实现每个触发词的语义分布式表示。
BackgroundIn biomedical research, events revealing complex relations between entities play an important role. Biomedical event trigger identification has become a research hotspot since its important role in biomedical event extraction. Traditional machine learning methods, such as support vector machines (SVM) and maxent classifiers, which aim to manually design powerful features fed to the classifiers, depend on the understanding of the specific task and cannot generalize to the new domain or new examples.MethodsIn this paper, we propose an approach which utilizes neural network model based on dependency-based word embedding to automatically learn significant features from raw input for trigger classification. First, we employ Word2vecf, the modified version of Word2vec, to learn word embedding with rich semantic and functional information based on dependency relation tree. Then neural network architecture is used to learn more significant feature representation based on raw dependency-based word embedding. Meanwhile, we dynamically adjust the embedding while training for adapting to the trigger classification task. Finally, softmax classifier labels the examples by specific trigger class using the features learned by the model.ResultsThe experimental results show that our approach achieves a micro-averaging F1 score of 78.27 and a macro-averaging F1 score of 76.94 % in significant trigger classes, and performs better than baseline methods. In addition, we can achieve the semantic distributed representation of every trigger word.