拼写错误纠正是自然语言处理中具有很长历史的主题之一。虽然以前的研究取得了显着的结果,但仍然存在挑战。在越南语中,任务的最先进的方法从其相邻音节中介绍了一个音节的上下文。然而,该方法的准确性可能是不令人满意的,因为如果模型可能会失去上下文,如果两个(或更多)拼写错误彼此静置。在本文中,我们提出了一种纠正越南拼写错误的新方法。我们使用深入学习模型解决错误错误和拼写错误错误的问题。特别地,嵌入层由字节对编码技术提供支持。基于变压器架构的序列模型的序列使我们的方法与上一个问题不同于同一问题的方法。在实验中,我们用大型合成数据集训练模型,这是随机引入的拼写错误。我们使用现实数据集测试所提出的方法的性能。此数据集包含11,202个以9,341不同的越南句子中的人造拼写错误。实验结果表明,我们的方法达到了令人鼓舞的表现,检测到86.8%的误差,81.5%纠正,分别提高了最先进的方法5.6%和2.2%。
translated by 谷歌翻译
For solving a broad class of nonconvex programming problems on an unbounded constraint set, we provide a self-adaptive step-size strategy that does not include line-search techniques and establishes the convergence of a generic approach under mild assumptions. Specifically, the objective function may not satisfy the convexity condition. Unlike descent line-search algorithms, it does not need a known Lipschitz constant to figure out how big the first step should be. The crucial feature of this process is the steady reduction of the step size until a certain condition is fulfilled. In particular, it can provide a new gradient projection approach to optimization problems with an unbounded constrained set. The correctness of the proposed method is verified by preliminary results from some computational examples. To demonstrate the effectiveness of the proposed technique for large-scale problems, we apply it to some experiments on machine learning, such as supervised feature selection, multi-variable logistic regressions and neural networks for classification.
translated by 谷歌翻译
Adversarial machine learning has been both a major concern and a hot topic recently, especially with the ubiquitous use of deep neural networks in the current landscape. Adversarial attacks and defenses are usually likened to a cat-and-mouse game in which defenders and attackers evolve over the time. On one hand, the goal is to develop strong and robust deep networks that are resistant to malicious actors. On the other hand, in order to achieve that, we need to devise even stronger adversarial attacks to challenge these defense models. Most of existing attacks employs a single $\ell_p$ distance (commonly, $p\in\{1,2,\infty\}$) to define the concept of closeness and performs steepest gradient ascent w.r.t. this $p$-norm to update all pixels in an adversarial example in the same way. These $\ell_p$ attacks each has its own pros and cons; and there is no single attack that can successfully break through defense models that are robust against multiple $\ell_p$ norms simultaneously. Motivated by these observations, we come up with a natural approach: combining various $\ell_p$ gradient projections on a pixel level to achieve a joint adversarial perturbation. Specifically, we learn how to perturb each pixel to maximize the attack performance, while maintaining the overall visual imperceptibility of adversarial examples. Finally, through various experiments with standardized benchmarks, we show that our method outperforms most current strong attacks across state-of-the-art defense mechanisms, while retaining its ability to remain clean visually.
translated by 谷歌翻译
Pareto Front Learning (PFL) was recently introduced as an effective approach to obtain a mapping function from a given trade-off vector to a solution on the Pareto front, which solves the multi-objective optimization (MOO) problem. Due to the inherent trade-off between conflicting objectives, PFL offers a flexible approach in many scenarios in which the decision makers can not specify the preference of one Pareto solution over another, and must switch between them depending on the situation. However, existing PFL methods ignore the relationship between the solutions during the optimization process, which hinders the quality of the obtained front. To overcome this issue, we propose a novel PFL framework namely \ourmodel, which employs a hypernetwork to generate multiple solutions from a set of diverse trade-off preferences and enhance the quality of the Pareto front by maximizing the Hypervolume indicator defined by these solutions. The experimental results on several MOO machine learning tasks show that the proposed framework significantly outperforms the baselines in producing the trade-off Pareto front.
translated by 谷歌翻译
无线传感器网络由随机分布的传感器节点组成,用于监视目标或感兴趣的区域。由于每个传感器的电池容量有限,因此维持连续监视的网络是一个挑战。无线电源传输技术正在作为可靠的解决方案,用于通过部署移动充电器(MC)为传感器充电传感器。但是,由于网络中出现不确定性,为MC设计最佳的充电路径是具有挑战性的。由于网络拓扑的不可预测的变化,例如节点故障,传感器的能耗率可能会显着波动。这些变化也导致每个传感器的重要性变化,在现有作品中通常被认为是相同的。我们在本文中提出了一种使用深度强化学习(DRL)方法提出新颖的自适应充电方案,以解决这些挑战。具体来说,我们赋予MC采用充电策略,该策略确定了下一个在网络当前状态上充电条件的传感器。然后,我们使用深层神经网络来参数这项收费策略,该策略将通过强化学习技术进行培训。我们的模型可以适应网络拓扑的自发变化。经验结果表明,所提出的算法的表现优于现有的按需算法的大幅度边缘。
translated by 谷歌翻译
本文报道的研究通过应用计算机视觉技术将普通的垃圾桶转化为更聪明的垃圾箱。在传感器和执行器设备的支持下,垃圾桶可以自动对垃圾进行分类。特别是,垃圾箱上的摄像头拍摄垃圾的照片,然后进行中央处理单元分析,并决定将垃圾桶放入哪个垃圾箱中。我们的垃圾箱系统的准确性达到90%。此外,我们的模型已连接到Internet,以更新垃圾箱状态以进行进一步管理。开发了用于管理垃圾箱的移动应用程序。
translated by 谷歌翻译
代码转换(CS)是多语言个体所表现出的常见语言现象,在一次对话中,它们倾向于在语言之间交替。 CS是一种复杂的现象,不仅包含语言挑战,而且还包含大量的复杂性,就其在说话者之间的动态行为而言。鉴于产生CS的因素因一个国家而异,并且从一个人到另一个人都不同,因此发现CS是一种依赖说话者的行为,在该行为中,外语被嵌入的频率在说话者之间有所不同。尽管几位研究人员从语言的角度研究了CS行为,但研究仍然缺乏从社会学和心理学角度预测用户CS行为的任务。我们提供了一项经验用户研究,我们研究用户的CS级别和性质特征之间的相关性。我们对双语者进行访谈,并收集有关他们的个人资料的信息,包括他们的人口统计学,个性特征和旅行经验。然后,我们使用机器学习(ML)根据其配置文件来预测用户的CS级别,在此我们确定建模过程中的主要影响因素。我们试验分类和回归任务。我们的结果表明,CS行为受到说话者之间的关系,旅行经验以及神经质和外向性人格特征的影响。
translated by 谷歌翻译
自Bert(Devlin等,2018)以来,学习上下文化的单词嵌入一直是NLP中的事实上的标准。然而,学习上下文化短语嵌入的进展受到缺乏人类通知的语句基准基准的阻碍。为了填补这一空白,我们提出了PIC- 〜28K名词短语的数据集伴随着它们的上下文Wikipedia页面,以及一套三个任务,这些任务增加了评估短语嵌入质量的难度。我们发现,在我们的数据集中进行的培训提高了排名模型的准确性,并明显地将问题答案(QA)模型推向了近人类的准确性,而在语义搜索上,鉴于询问短语和段落,在语义搜索上是95%的精确匹配(EM)。有趣的是,我们发现这种令人印象深刻的性能的证据是因为质量检查模型学会了更好地捕获短语的共同含义,而不管其实际背景如何。也就是说,在我们的短语中歧义歧义(PSD)任务上,SOTA模型的精度大大下降(60%EM),在两个不同情况下未能区分相同短语的两种不同感觉。在我们的3任任务基准测试中的进一步结果表明,学习上下文化的短语嵌入仍然是一个有趣的开放挑战。
translated by 谷歌翻译
诗歌的语音综合是由于诗意语音固有的特定语调模式而具有挑战性的。在这项工作中,我们提出了一种将诗歌与几乎像人类一样自然的综合诗作的方法,以使文学学者能够系统地检查有关文本,口头实现和听众对诗歌的相互作用的假设。为了满足文学研究的这些特殊要求,我们通过从人类参考朗诵中克隆韵律价值来重新合成诗,然后利用细粒度的韵律控制来操纵在人类的环境中的合成语音以改变朗诵W.R.T.具体现象。我们发现,对诗歌的TTS模型进行鉴定会在很大程度上捕捉诗歌语调模式,这对韵律克隆和操纵是有益的,并在客观评估和人类研究中都验证了我们方法的成功。
translated by 谷歌翻译
在这项工作中,我们提出了一个说话者的匿名管道,该管道利用高质量的自动语音识别和合成系统来生成以语音转录和匿名扬声器嵌入为条件的语音。使用电话作为中间表示,可确保从输入中完全消除说话者身份信息,同时尽可能保留原始的语音内容。我们在Librispeech和VCTK Corpora上的实验结果揭示了两个关键发现:1)尽管自动语音识别会产生不完美的转录,但我们的神经语音合成系统可以处理此类错误,使我们的系统可行且健壮,并且2)结合来自不同资源的扬声器嵌入,有益及其适当的归一化至关重要。总体而言,我们的最终最佳系统在2020年语音隐私挑战挑战中提供的基线在与懒惰的攻击者的稳健性方面相当大,同时保持了匿名语音的高度理解性和自然性。
translated by 谷歌翻译