A Multi-Label Classification Method on Chinese Temporal Expressions Based on Character Embedding

Understanding temporal expressions is the important foundation of many NLP tasks. However, the varied representations of temporal expressions is difficulty in analysis and understanding. To parsing expressions, an effective classification method of temporal expressions is significant. A temporal expression may belong to one or more classes, but the classification usually requires manual annotation characteristics. In this paper, we present a character embedding feature method based on distributed word representation and a multi-label classification method based on neural network. The Chinese temporal expressions can be classified automatically by their characteristics. Experiments on TempEval-2 datasets show that our method has achieved good performance.