End-2-End(E2E)模型由于其性能和优势而在某些ASR任务中变得越来越流行。这些E2E模型直接近似鉴于声学输入的代币的后验分布。因此,E2E系统在输出令牌上隐式定义了语言模型(LM),这使得对独立训练的语言模型的开发不如常规ASR系统不那么直接。这使得很难动态地调整E2E ASR系统,以更好地识别诸如命名实体之类的特殊单词。在这项工作中,我们提出了一种培训上下文意识到的E2E模型和将语言模型调整为命名实体的上下文密度比率方法。我们将上述技术应用于E2E ASR系统,该系统会转录医生和患者对话,以更好地适应E2E系统对对话中的名称。我们提出的技术在E2E基线上的名称相对提高了46.5%,而不会降低整个测试集的总体识别精度。此外,它还相对超过了上下文浅融合基线的22.1%。
translated by 谷歌翻译
RNN-T模型由于其在线流媒体模式下运营的竞争力和能力,因此在文献和商业系统中广受欢迎。在这项工作中,我们进行了一项广泛的研究,比较了单调和原始RNN-T模型的几种预测网络体系结构。我们根据普通的最新构象编码器比较4种类型的预测网络,并在LibrisPeech和内部医学对话数据集上获得报告结果。我们的研究涵盖了离线批处理模式和在线流媒体方案。与以前的一些作品相反,我们的结果表明,当用作预测网络以及构象异构体编码器时,变压器并不总是胜过LSTM。受分数启发的启发,我们提出了一个新的简单预测网络体系结构N-CONCAT,它在我们在线流式传输基准测试中的表现优于其他。变压器和N-Gram降低的体系结构的表现非常相似,但在先前的上下文方面具有一些重要的不同行为。总体而言,与LSTM基线相比,我们获得了多达4.1%的相对相对改善,同时将预测网络参数降低了几乎数量级(8.4倍)。
translated by 谷歌翻译
Spacecraft pose estimation is a key task to enable space missions in which two spacecrafts must navigate around each other. Current state-of-the-art algorithms for pose estimation employ data-driven techniques. However, there is an absence of real training data for spacecraft imaged in space conditions due to the costs and difficulties associated with the space environment. This has motivated the introduction of 3D data simulators, solving the issue of data availability but introducing a large gap between the training (source) and test (target) domains. We explore a method that incorporates 3D structure into the spacecraft pose estimation pipeline to provide robustness to intensity domain shift and we present an algorithm for unsupervised domain adaptation with robust pseudo-labelling. Our solution has ranked second in the two categories of the 2021 Pose Estimation Challenge organised by the European Space Agency and the Stanford University, achieving the lowest average error over the two categories.
translated by 谷歌翻译
Privacy-preserving machine learning in data-sharing processes is an ever-critical task that enables collaborative training of Machine Learning (ML) models without the need to share the original data sources. It is especially relevant when an organization must assure that sensitive data remains private throughout the whole ML pipeline, i.e., training and inference phases. This paper presents an innovative framework that uses Representation Learning via autoencoders to generate privacy-preserving embedded data. Thus, organizations can share the data representation to increase machine learning models' performance in scenarios with more than one data source for a shared predictive downstream task.
translated by 谷歌翻译
In this work, we propose a framework relying solely on chat-based customer support (CS) interactions for predicting the recommendation decision of individual users. For our case study, we analyzed a total number of 16.4k users and 48.7k customer support conversations within the financial vertical of a large e-commerce company in Latin America. Consequently, our main contributions and objectives are to use Natural Language Processing (NLP) to assess and predict the recommendation behavior where, in addition to using static sentiment analysis, we exploit the predictive power of each user's sentiment dynamics. Our results show that, with respective feature interpretability, it is possible to predict the likelihood of a user to recommend a product or service, based solely on the message-wise sentiment evolution of their CS conversations in a fully automated way.
translated by 谷歌翻译
We present the GPry algorithm for fast Bayesian inference of general (non-Gaussian) posteriors with a moderate number of parameters. GPry does not need any pre-training, special hardware such as GPUs, and is intended as a drop-in replacement for traditional Monte Carlo methods for Bayesian inference. Our algorithm is based on generating a Gaussian Process surrogate model of the log-posterior, aided by a Support Vector Machine classifier that excludes extreme or non-finite values. An active learning scheme allows us to reduce the number of required posterior evaluations by two orders of magnitude compared to traditional Monte Carlo inference. Our algorithm allows for parallel evaluations of the posterior at optimal locations, further reducing wall-clock times. We significantly improve performance using properties of the posterior in our active learning scheme and for the definition of the GP prior. In particular we account for the expected dynamical range of the posterior in different dimensionalities. We test our model against a number of synthetic and cosmological examples. GPry outperforms traditional Monte Carlo methods when the evaluation time of the likelihood (or the calculation of theoretical observables) is of the order of seconds; for evaluation times of over a minute it can perform inference in days that would take months using traditional methods. GPry is distributed as an open source Python package (pip install gpry) and can also be found at https://github.com/jonaselgammal/GPry.
translated by 谷歌翻译
可以通过玩游戏来训练代理商来回答困难的数学问题吗?我们考虑了整数可行性问题,这是决定线性方程和不平等系统是否具有具有整数值的解决方案的挑战。对于许多数学和计算机科学领域的应用,这是一个著名的NP完整问题。我们的论文描述了一个新颖的代数增强学习框架,该框架使代理商可以玩相当于整数可行性问题的游戏。我们解释了如何将整数可行性问题转换为具有固定保证金总和的一组阵列的游戏。游戏从初始状态(数组)开始,并采取法律举措使利润率保持不变,我们的目标是最终与零位置的零位置达到胜利状态。为了赢得比赛,玩家必须在初始状态和最终终端获胜状态之间找到一条路径。找到这样的获胜状态等同于解决整数可行性问题。关键代数成分是“基础轴向运输polyhedron的曲折理想的基础”。gr \'obner可以看作是游戏的一组连接移动(动作)。然后,我们提出了一种新型的RL方法,该方法训练代理以预测连续空间中的移动,以应对较大的动作空间。然后将连续的移动投射到一组法律移动上,以使该路径始终导致有效状态。作为概念的证明,我们在实验中证明了我们的代理商可以很好地发挥我们最简单的游戏版本,用于2向表。我们的工作突出了培训代理商通过当代机器学习方法来训练代理商玩游戏的潜力来解决非平凡的数学查询的潜力。
translated by 谷歌翻译
考虑到大量未标记的语音数据和高标签成本,无监督的学习方法对于更好的系统开发至关重要。最成功的方法之一是对比度的自我监督方法,这些方法需要负采样:采样替代样品与当前样品(锚)对比。但是,很难确保所有负样本属于与没有标签的锚类别不同的​​类别。本文在未标记的语音语料库上应用了一种非对抗性的自我监督学习方法来学习话语级的嵌入。我们使用没有标签的蒸馏(Dino),在计算机视觉中提出,并将其改编为语音域。与对比度方法不同,Dino不需要负采样。这些嵌入是根据说话者验证和情感识别评估的。在说话者验证中,无监督的恐龙与余弦评分嵌入了voxceleb1测试试验中的4.38%EER。这表现优于最佳的对比度自我监督方法,而EER中的相对相对40%。不需要扬声器标签的迭代伪标记训练管道将EER进一步提高到1.89%。在情感识别中,Iemocap,Crema-D和MSP播客的Micro-F1得分分别进行了60.87、79.21和56.98%的恐龙。结果暗示着恐龙嵌入到不同语音应用中的普遍性。
translated by 谷歌翻译
本文通过数学形态的代数基础,分析了深卷积神经网络(DCNN)的非线性激活函数和空间最大化。此外,通过在形态代表的背景下考虑最大 - 释放和非线性算子,提出了一般的激活功能家族。实验部分验证了我们在经典基准测试中的方法,用于DCNN的监督学习。
translated by 谷歌翻译
预训练的语言模型的目的是学习文本数据的上下文表示。预训练的语言模型已成为自然语言处理和代码建模的主流。使用探针,一种研究隐藏矢量空间的语言特性的技术,以前的作品表明,这些预训练的语言模型在其隐藏表示中编码简单的语言特性。但是,以前的工作都没有评估这些模型是否编码编程语言的整个语法结构。在本文中,我们证明了\ textit {句法子空间}的存在,该{语法子空间}位于预训练的语言模型的隐藏表示中,其中包含编程语言的句法信息。我们表明,可以从模型的表示形式中提取此子空间,并定义一种新颖的探测方法AST-Probe,该方法可以恢复输入代码段的整个抽象语法树(AST)。在我们的实验中,我们表明这种句法子空间存在于五个最先进的预训练的语言模型中。此外,我们强调说,模型的中间层是编码大多数AST信息的模型。最后,我们估计该句法子空间的最佳大小,并表明其尺寸大大低于模型的表示空间。这表明,预训练的语言模型使用其表示空间的一小部分来编码编程语言的句法信息。
translated by 谷歌翻译