ID 原文 译文
1133 其次，解决了 16 阶ARIA 型扩散结构分支数为 8 的计数问题， Secondly, the counting problem of 16-order ARIA-type diffusion structures with the branch number 8 is solved.
1134 最后，给出了分支数为 8 的 16 阶对合 ARIA 型扩散结构的构造方法。 Finally, the construction methods of the 16-order involution ARIA-type diffu-sion structure are given.
1135 本文的研究成果为构造分支数达到最大的 16 阶对合二元方阵提供了一种新方法。 The research results of this paper provide a method for constructing 16-order involution binary ma-trix with the largest branch number.
1136 命名实体识别与共指消解均依赖于对实体相邻文本信息的学习，本文提出一种基于混合神经网络的命名实体识别与共指消解联合模型， Considering that both named entity recognition and coreference resolution depend on the same context of the entity word, this paper proposes a hybrid neural network model to settle these problems which contains a named entityrecognition ( NER) module and a coreference resolution ( CR) module.
1137 共用双向长短时记忆模型 LSTM 编码层对输入序列中每个词前后方向上下文信息进行编码， NER and CR share the same bidirectional LSTM en-coding layer, which is used to encode each input word by taking into account the context on both sides of the word.
1138 并通过训练学习得到上下文信息传递到前馈神经网络 FFNN 模型以提高共指消解精度， The con-textual information of entities obtained in BiLSTM encoding layer further pass through to FFNN module to improve the core-ference resolution.
1139 通过将领域文档及篇章语义向量加入 FFNN，改进共指消解算法并优化共指消解模型。 Furthermore, by adding domain documents and chapter semantic vectors to FFNN, the coreference resolu-tion algorithm is improved and the coreference resolution model is optimized.
1140 基于领域文本数据集进行联合模型训练，实验结果表明该联合模型可以有效地提高共指消解精度。 Finally, we conduct experiments on the domain dataset to verify the effectiveness of our method. The joint model can effectively improve the accuracy of coreference resolu-tion task.
1141 具有低失真、强鲁棒等特点的直方图数字水印算法，一直是信息隐藏领域研究的热点。 The histogram shape-based digital watermarking, which has the characteristics of low distortion, strong ro-bustness, and etc, has become a hot topic in information hiding fields.
1142 本文在分析现有直方图数字水印算法的基础上，提出并设计了基于直方图修改的 2Bin 多进制图像水印算法。 Upon the basic properties of the existing histogramshape-based digital watermarking, a modified histogram shape-based 2Bin M-ary digital watermarking algorithm is designed firstly,