Zhen Yang, Wei Chen, Feng Wang, Bo Xu. Proceedings of the 2018 Conference North American Chapter Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). 2018.

Unsupervised neural machine translation (NMT) is a recently proposed approach for which aims to train the model without using any labeled data. The models unsupervised NMT often use only one shared encoder map pairs of sentences from different languages shared-latent space, weak in keeping unique and internal characteristics each language, such as style, terminology, sentence structure. To address this issue, we introduce an extension by utilizing two independent encoders but sharing some...

In the "Internet Plus" era, space-based information services require effective and fast image satellite scheduling. Most existing studies consider scheduling to be an optimization problem solve with searching algorithms in a batch-wise manner. No real-time speed method for exists. this paper, idea of building method, is remodeled based on Dynamic Stochastic Knapsack Problem (DSKP), objective maximize total expected profit. algorithm could able novel properly. With inspiration from recent...

With the development of unmanned aerial vehicle (UAV) and artificial intelligence (AI) technology, Intelligent UAV will be widely used in future autonomous combat. Previous researches on combat within visual range (WVR) have limitations due to simplifying assumptions, limited robustness, ignoring sensor errors. In this paper, order consider error aircraft sensors, we model WVR as a state-adversarial Markov decision process (SA-MDP), which introduce small adversarial perturbations state...

This paper proposes a new pre-training method, called Code-Switching Pre-training (CSP for short) Neural Machine Translation (NMT). Unlike traditional method which randomly masks some fragments of the input sentence, proposed CSP replaces words in source sentence with their translation target language. Specifically, we firstly perform lexicon induction unsupervised word embedding mapping between and languages, then replace according to extracted lexicons. adopts encoder-decoder framework:...

Distributed multi-agent collaborative decision-making technology is the key to general artificial intelligence. This paper takes self-developed Unity3D combat environment as test scenario, setting a task that requires heterogeneous unmanned aerial vehicles (UAVs) perform distributed and complete cooperation task. Aiming at problem of traditional proximal policy optimization (PPO) algorithm’s poor performance in field complex collaboration scenarios based on training framework Ray, Critic...

Graph Neural Networks (GNNs) have achieved tremendous success in graph representation learning. Unfortunately, current GNNs usually rely on loading the entire attributed into network for processing. This implicit assumption may not be satisfied with limited memory resources, especially when is large. In this paper, we pioneer to propose a Binary Convolutional Network (Bi-GCN), which binarizes both parameters and input node features. Besides, original matrix multiplications are revised binary...

Online accurate recognition of target tactical intention in beyond-visual-range (BVR) air combat is an important basis for deep situational awareness and autonomous decision-making, which can create pre-emptive opportunities the fighter to gain superiority. The existing methods solve this problem have some defects such as dependence on empirical knowledge, difficulty interpreting results, inability meet requirements actual combat. So online hierarchical method BVR based cascaded support...

A comparative study of high chromium (Super304H) and manganese low heat-resistant steel (HT630) was carried out at 650°C in steam. Results indicate that the content HT630 significantly improved its oxidation resistance. It is ascribed to formation a dense protective MnCr2O4 oxide layer during oxidation. effectively inhibits diffusion iron, suppresses growth iron-rich oxides, promotes an interface with matrix, improves overall

To study the characteristics of ozone formation sensitivity changes in Chengdu-Chongqing area, summer （OFS） was analyzed using satellite observation OMI tropospheric column concentration HCHO and NO2. Additionally, effects meteorological factors, source emissions, their interactions on OFS were identified with geodetic detector. The results showed that zoning area dominated by a transitional regime, an share 42.42%. Less VOCs-limited regime observed, which mainly distributed urban areas...

A novel method for switch-controlled drug release was developed through reversible morphology transitions from vesicles to nanoparticles based on supramolecular branched copolymer self-assemblies.

This research on identification and classification of construction workers’ activity contributes to the monitoring management individuals. Since a single sensor cannot meet requirements complex environment, integrated multiple sensors usually lack systemic flexibility stability, this paper proposes an approach construction-activity recognition based smartphones. The accelerometers gyroscopes embedded in smartphones were utilized collect three-axis acceleration angle data eight main...

This study deals with the autonomous evasive maneuver strategy of unmanned combat air vehicle (UCAV), which is threatened by a high-performance beyond-visual-range (BVR) air-to-air missile (AAM). Considering tactical demands achieving self-conflicting objectives in actual combat, including higher miss distance, less energy consumption and longer guidance support time, problem BVR defined reformulated into multi-objective optimization problem. Effective maneuvers UCAV used different evasion...

Combining global and local search is a strategy used by many successful hybrid optimization approaches. Memetic Algorithms (MAs) are Evolutionary (EAs) that apply some sort of to further improve the fitness individuals in population. have been shown be very effective solving hard combinatorial problems. This paper provides forum for identifying exploring key issues affect design application Algorithms. The approach combines hierarchical technique, Genetic Algorithms, constructive techniques...

This study provides an effective strategy for preparing a crown ether-based <bold>A2</bold>-<bold>B3</bold>-type supramolecular hyperbranched polymer with stimuli-responsive behavior.

With the development of unmanned combat air vehicles (UCAVs) and artificial intelligence (AI), within visual range (WVR) confrontations utilizing intelligent UCAVs are expected to be widely used in future combats. As controlling highly dynamic uncertain WVR combats from ground stations UCAV is not feasible, it necessary develop an algorithm that can generate strategies order enable independently complete missions. In this paper, a 1-vs.-1 strategy generation proposed using multi-agent deep...

Improvement of integrated battlefield situational awareness in complex environments involving dynamic factors such as restricted communications and electromagnetic interference (EMI) has become a contentious research problem. In certain mission environments, due to the impact many sources on real-time communication or requirements need implement regulations, stages are represented combination several communication-available communication-unavailable stages. Furthermore, data interaction...

Photo-controlled host–guest interaction is used to improve the core removal method for preparing “breathing” hollow nanospheres as drug delivery.