基于分层输出神经网络的汉语语义角色标注

Chinese Semantic Role Labeling Based on Neural Network with Optimized Output Layer

语义角色标注是自然语言处理中的一项重要任务。当下针对中文语义角色标注的主流做法是通过基于特征的统计机器学习实现的。然而,统计机器学习的方法需要引入经验性的人工特征,这在一定程度上增加了工作量。深度学习在自然语言处理领域的应用使得特征的自动学习成为可能。文章尝试了一种适用于语义角色标注的深层神经网络架构,该模型能自然地推广到其他标注任务。实验表明,深度学习算法能够有效地用于语义角色标注任务,但是我们仍然发现,模型对语义层面知识的学习是相当有限的,基于深度学习的方法还不能取代基于人工特征的统计机器学习算法。

Semantic role labeling is an important task in Chinese natural language processing. Using feature based statistical machine learning to perform semantic role labeling is the mainstream method nowadays, denpeding heavily on manually designed features. This paper investigates semantic role labeling based on deep neural nets, which can learn features automatically. Experimental results show that our algorithm is promising. However, it cannot reach conventional machine learning methods with manually designed features yet.