Neural Chinese Word Segmentation as Sequence to Sequence Translation
This work addresses Chinese word segmentation for natural language processing applications, presenting an incremental approach by applying a known sequence-to-sequence framework to this task.
The authors tackled Chinese word segmentation by framing it as a sequence-to-sequence translation problem using an attention-based encoder-decoder model, which achieved competitive performance on benchmark datasets like Weibo, PKU, and MSRA. They also demonstrated the model's applicability by jointly learning Chinese word segmentation with Chinese spelling correction in an end-to-end manner.
Recently, Chinese word segmentation (CWS) methods using neural networks have made impressive progress. Most of them regard the CWS as a sequence labeling problem which construct models based on local features rather than considering global information of input sequence. In this paper, we cast the CWS as a sequence translation problem and propose a novel sequence-to-sequence CWS model with an attention-based encoder-decoder framework. The model captures the global information from the input and directly outputs the segmented sequence. It can also tackle other NLP tasks with CWS jointly in an end-to-end mode. Experiments on Weibo, PKU and MSRA benchmark datasets show that our approach has achieved competitive performances compared with state-of-the-art methods. Meanwhile, we successfully applied our proposed model to jointly learning CWS and Chinese spelling correction, which demonstrates its applicability of multi-task fusion.