This paper considers the problem of learning Chinese word embeddings. In contrast to English, a Chinese word is usually composed of characters, and most of the characters themselves can be further divided into components such as radicals. While characters and radicals contain rich information and are capable of indicating semantic meanings of words, they have not been fully exploited by existing word embedding methods. In this work, we propose multi-granularity embedding (MGE) for Chinese words. The key idea is to make full use of such word-character-radical composition, and enrich word embeddings by further incorporating finer-grained semantics from characters and radicals. Quantitative evaluation demonstrates the superiority of MGE in word similarity computation and analogical reasoning. Qualitative analysis further shows its capability to identify finer-grained semantic meanings of words.

No abstract

InGaAs/InP single-photon avalanche diodes (SPADs) working in the regime of GHz clock rates are crucial components for the high-speed quantum key distribution (QKD). We have developed for the first time a compact, stable and user-friendly tabletop InGaAs/InP single-photon detector system operating at a 1.25 GHz gate rate that fully integrates functions for controlling and optimizing SPAD performance.We characterize the key parameters of the detector system and test the long-term stability of the system for continuous operation of 75 hours. The detector system can substantially enhance QKD performance and our present work paves the way for practical high-speed QKD applications.

A sophisticated hierarchical neural network model for intelligent assessment of structural damage is constructed by the synergetic action of auto-associative neural networks (AANNs) and Levenberg-Marquardt neural networks (LMNNs). With the model, AANNs aided by the wavelet packet transform are firstly employed to extract damage features from measured dynamic responses and LMNNs are then utilized to undertake damage pattern recognition. The synergetic functions endow the model with a unique mechanism of intelligent damage identification in structures. The model is applied for the identification of damage in a three-span continuous bridge, with particular emphasis on noise interference. The results show that the AANNs can produce a low-dimensional space of damage features, from which LMNNs can recognize both the location and the severity of structural damage with great accuracy and strong robustness against noise. The proposed model holds promise for developing viable intelligent damage identification technology for actual engineering structures.

No abstract