ID 原文 译文
25365 两个模块并行相互提升，可以得到完整的特征表示。 The two modules promote each other in parallel to obtain complete feature representation.
25366 在 TA-CＲED 和 SemEval 数据集上的实验结果表明，该方法能够更有效地获取对关系抽取任务有益的信息，在各评价指标上取得了更好的性能。 The experimental results on the TACＲED and SemEval datasets show that the method can obtain more useful information for relation extraction, thus achieve better performances on various evaluation metrics．
25367 现有深度学习方法在对时间序列预测时，未充分考虑空间依赖性，且长期预测的准确率也较低。 There are various deep learning methods already implemented in time-series forecasting problems, and some of them show better performance and adaptability than the methods based on statistics. However, the spatial dependence implicit in multiple series usually is not considered within the existing time-series forecasting methods, which also results in unsatisfactory performance in long-term forecasting．
25368 针对此问题，提出一种融合时间序列分解策略和时空卷积神经网络的时序预测模型 SDBＲNN(Series-Decomposition-Block Ｒe-current Neural Network)。 Thus, we propose a model series-decomposition-block recurrent neural network (SDBＲNN), which fuses time-series decomposition strategy and the spatio-temporal convolutional layer．
25369 该模型首先学习序列的多周期值并对序列进行最优 STL 分解;然后结合相邻观察点构造兼具时空数据块; This model relies on an improved STL decomposition strategy to get optimal series-components and to combine them into spatio-temporal blocks．
25370 再采用 Block-LSTM 中的三维卷积模块对时空数据块进行特征提取，让三维块在 LSTM 细胞中参与状态更新和反向传播，最终实现模型对时空特征的学习。 Then an long-short term memory (LSTM) variant network called Block-LSTM is used to extract spatio-temporal features from blocks and achieve forecasting．
25371 结合多个时空序列测试数据分析，表明该模型在具有空间依赖关系的时序数据集上，比传统的时间卷积模型和循环神经网络具有更好的时空特征提取能力和拟合预测能力，验证了该模型的有效性。 Experiments on real-world datasets proved that the model has excellent capabilities of feature extraction and long-term forecasting compared with other methods such as temporal convolutional network and recurrent neural network．
25372 本文介绍三值光学计算机的一种新型并行加法器—SJ-MSD 加法器的设计与实现。 In this paper the design and implementation of a new parallel adder, SJ-MSD adder, in a ternary optical computer (i. e. TOC) are proposed．
25373 介绍判断一组三值逻辑变换能够实现并行无连续进位二进制 MSD 数加法的充分条件(沈氏充分性定理)。 It is introduced that a sufficient conditions (Shen's sufficient theorem) which judging that a group of ternary logical transformations is able to build a MSD (Modified Signed Digit) addition．
25374 给出了构成 SJ-MSD 加法器的五个三值逻辑变换:S1、S2、J1、J2和 J3(简称 SJ 变换)，及其操作规则(简称 SJ 规则)，并依据沈氏充分性定理推证了 SJ变换和 SJ 规则构成 MSD 并行加法器的可靠性。 Five logical transformations S1, S2，J1，J2 and J3 (i． e． SJ transformation) and a parallel carry-free MSD addition rule (i.e. SJ rule) are proposed to construct SJ-MSD adder. Meanwhile according to Shen's sufficient theorem, the reliability of the SJ transformation and SJ rule used to construct MSD parallel adder is proved．