Currently most of state-of-the-art methods for Chinese word segmentation are based on supervised learning, whose features are mostly extracted from a local context. These methods cannot utilize the long distance information which is also crucial for word segmentation. In this paper, we propose a novel neural network model for Chinese word segmentation, which adopts the long short-term memory (LSTM) neural network to keep the previous important information in memory cell and avoids the limit of window size of local context. Experiments on PKU, MSRA and CTB6 benchmark datasets show that our model outperforms the previous neural network models and state-of-the-art methods.

Recently, neural network models for natural language processing tasks have been increasingly focused on for their ability of alleviating the burden of manual feature engineering. However, the previous neural models cannot extract the complicated feature compositions as the traditional methods with discrete features. In this paper, we propose a gated recursive neural network (GRNN) for Chinese word segmentation, which contains reset and update gates to incorporate the complicated combinations of the context characters. Since GRNN is relative deep, we also use a supervised layer-wise training method to avoid the problem of gradient diffusion. Experiments on the benchmark datasets show that our model outperforms the previous neural network models as well as the state-of-the-art methods.

No abstract

No abstract

Anew bicyclic diterpenoid, benditerpenoic acid, was isolated from soil-dwelling Streptomyces sp.( CL12-4). We sequenced the bacterial genome,i dentified the responsible biosynthetic gene cluster,v erified the function of the terpene synthase,a nd heterologously produced the core diterpene. Comparative bioinformatics indicated this Streptomyces strain is phylogenetically unique and possesses nine terpene synthases.The absolute configurations of the new trans-fused bicyclo-[8.4.0]tetradecanes were achieved by extensive spectroscopic analyses,i ncluding Moshersa nalysis,J -based coupling analysis,a nd computations based on sparse NMR-derived experimental restraints.I nterestingly,b enditerpenoic acid exists in two distinct ring-flipped bicyclic conformations with ar otational barrier of % 16 kcal mol À1 in solution. The diterpenes exhibit moderate antibacterial activity against Gram-positive bacteria including methicillin and multi-drug resistant Staphylococcus aureus.This is arare example of an eunicellane-type diterpenoid from bacteria and the first identification of ad iterpene synthase and biosynthetic gene cluster responsible for the construction of the eunicellane scaffold.

No abstract

In this work, we address the problem to model all the nodes (words or phrases) in a dependency tree with the dense representations. We propose a recursive convolutional neural network (RCNN) architecture to capture syntactic and compositional-semantic representations of phrases and words in a dependency tree. Different with the original recursive neural network, we introduce the convolution and pooling layers, which can model a variety of compositions by the feature maps and choose the most informative compositions by the pooling layers. Based on RCNN, we use a discriminative model to re-rank a k-best list of candidate dependency parsing trees. The experiments show that RCNN is very effective to improve the state-of-the-art dependency parsing on both English and Chinese datasets.

Abstract-Machine-to-Machine (M2M) communication is now playing a market-changing role in a wide range of business world. However, in event-driven M2M communications, a large number of devices activate within a short period of time, which in turn causes high radio congestions and severe access delay. To address this issue, we propose a Fast Adaptive S-ALOHA (FASA) scheme for M2M communication systems with bursty traffic. The statistics of consecutive idle and collision slots, rather than the observation in a single slot, are used in FASA to accelerate the tracking process of network status. Furthermore, the fast convergence property of FASA is guaranteed by using drift analysis. Simulation results demonstrate that the proposed FASA scheme achieves near-optimal performance in reducing access delay, which outperforms that of traditional additive schemes such as PB-ALOHA. Moreover, compared to multiplicative schemes, FASA shows its robustness even under heavy traffic load in addition to better delay performance.