A local and global context representation learning model for Chinese characters is designed and a Chinese word segmentation method based on character representations is proposed in this paper. First, the proposed Chinese character learning model uses the semanties of loeal context and global context to learn the representation of Chinese characters. Then, Chinese word segmentation model is built by a neural network, while the segmentation model is trained with the eharaeter representations as its input features. Finally, experimental results show that Chinese charaeter representations can effectively learn the semantic information. Characters with similar semantics cluster together in the visualize space. Moreover, the proposed Chinese word segmentation model also achieves a pretty good improvement on precision, recall and f-measure.
Almost all current automatic service composition （ASC） algorithms consider only single nonfunctional requirements, namely quality of service （QoS）, which cannot satisfy the real application. This paper proposes MAT （multi-QoS aware top-K ASC） algorithm to realize the high-efficiency exploring and rank- ing of composition scheme by synthesizing more nonfunctional goals. MAT algorithm explores composition schemes by the sky- line technique based on tape model and ranks these schemes by a modified binary tree. Using Web service challenge （WSC） 2009 dataset, we verify the performance of MAT algorithm and the experimental result is even close to the current fastest ASC algo- rithm considering only single QoS.
