ID 原文 译文
40276 预测模型和特征排序结果有助于企业制定最优的广告投放策略。 The prediction model and the result of feature ranking are helpful for the enterprise to make the optimal advertising strategy.
40277 x-vector系统将一段不定长的语音通过神经网络映射成固定维的矢量来表征说话人信息，该系统在文本无关的说话人确认(Speaker verification，SV)任务中取得了优异的性能。 The x-vector system maps a variable-length speech to a fixed-dimensional speaker embeddings via neural networks, and performs well in text-independent speaker verification.
40278 本文将其应用到文本相关的SV任务中，在x-vector模型选择上，采用残差神经网络以获得更有区分性的x-vector； Here, it is applied to the textdependent speaker verification and different x-vectors are extracted according to different contents in one sentence.In model selection, deep residual network(DRN)is used to obtain more discriminative x-vector.
40279 在包含多字符的语句中，对每个字训练一个残差神经网络；在提取过程中，每一字单独提取一个x-vector并单独进行说话人判决， For a sentence with multiple words, word-dependent DRNs are trained to extract word-dependent x-vectors, which are separately fed to different backend classifiers.
40280 最后将多个判决得分进行融合后给出最终的识别结果。 Finally, multiple scores are fused to obtain the final verification results.
40281 实验是在数据库RSR2015PartⅢ上进行的，提出的方法在男性和女性测试集上等错误率分别有15.34%、19.7%的下降。 Experiments on Part Ⅲ of the RSR2015 dataset show that the proposed method can achieve equal error rate(EER)reduction of 15.34% and 19.7% for male and female, respectively.
40282 现有的跨领域情感分类方法大多只利用了单个源域到目标域的迁移特征，没有充分考虑目标域实例与不同源域之间的联系。 Most of the existing cross-domain sentiment classification methods only take advantage of the migration feature from a single source domain to a target domain, without fully considering connections between target domain instances and different source domains.
40283 针对此问题，本文提出一种无监督的多源跨领域情感分类模型。 To solve this problem, this paper proposes an unsupervised multiple-source cross-domain sentiment classification model.
40284 首先利用单个源域到目标域的迁移特征训练基分类器，并对不同的基分类器加权； First, the base classifier is trained by using the migration feature of a single source domain to a target domain, and different base classifiers are weighted.
40285 然后将不同基分类器对目标域实例预测的集成一致性作为目标函数，优化该目标函数，得到不同基分类器的权重； Then, the ensemble consistency of different base classifiers on the target domain instance prediction is taken as the objective function, and the objective function is optimized to obtain the weights of different base classifiers.