Approaching Neural Chinese Word Segmentation as a Low-Resource Machine Translation Task

Chinese word segmentation has entered the deep learning era which greatly reduces the hassle of feature engineering. Recently, some researchers attempted to treat it as characterlevel translation, which further simplified model designing, but there is a performance gap between the translation-based approach and other methods. This motivates our work, in which we apply the best practices from lowresource neural machine translation to supervised Chinese segmentation. We examine a series of techniques including regularization, data augmentation, objective weighting, transfer learning, and ensembling. Compared to previous works, our low-resource translationbased method maintains the effortless model design, yet achieves the same result as state of the art in the constrained evaluation without using additional data.