框架识别是语义角色标注的基本任务,它是根据目标词激起的语义场景,为其分配一个合适的语义框架。目前框架识别的研究主要是基于统计机器学习方法,把它看作多分类问题,框架识别的性能主要依赖于人工选择的特征。然而,人工选择特征的有效性和完备性无法保证。深度神经网络自动学习特征的能力,为我们提供了新思路。该文探索了利用深度神经网络自动学习目标词上下文特征,建立了一种新的通用的框架识别模型,在汉语框架网和《人民日报》2003年3月新闻语料上分别取得了79.64%和78.58%的准确率,实验证明该模型具有较好的泛化能力。
Frame identification is a basic task of semantic role labeling,which assigns a correct frame to the labeled target word based on the semantic scene.At present,the state-of-the-art methods are primarily based on statistical machine learning,in which the performance heavily depends on the quality of the extracted features.This paper proposes a DNN based frame identification method,trying to capture the target word context automatically.Experiments on the Chinese FrameNet and the People's Daily(March,2003)show 79.64% and 78.58% accuracy,respectively.