Snorkel

Snorkel is an open-source system that introduces a new approach for rapidly creating, modeling, and managing data for training predictive systems. It is currently focused on accelerating the development of structured or "dark" data extraction applications for domains in which large labeled training sets are not available or easy to obtain. Examples include biomedical literature and clinical notes. Initial results show that Snorkel with its use of weakly labeled, noisy training data can achieve the same performance as fully supervised learning approaches with “gold standard” labeled training data.Snorkel has applicability in many domains. Example biomedical domains where Snorkel is being used include the microbiome, joint replacements, and cancer. To learn more or to download, visit http://snorkel.stanford.edu.To view recordings, slides, and other materials from the July 2017 workshop, click Downloads. <br/><br/>This project includes the following software/data packages: <br/> <ul> <li> <a href="https://simtk.org/frs?group_id=1263#pack_2060">Snorkel Workshop (Nov 2018) </a> : Materials from November 2018 Snorkel workshop. </li> <li> <a href="https://simtk.org/frs?group_id=1263#pack_1963">Snorkel Workshop (July 2017) </a> : Materials from July 2017 Snorkel workshop. </li> </ul>

Snorkel 是一款开源系统，它引入了一种新颖的方法，旨在快速构建、建模和管理用于训练预测系统的数据。该系统目前专注于加速结构化或所谓“暗数据”提取应用程序的开发，这类应用适用于难以获取或不存在大量标注训练集的领域。例如，生物医学文献和临床笔记。初步结果表明，Snorkel 通过使用弱标注、含噪声的训练数据，能够达到与使用“黄金标准”标注训练数据的完全监督学习方法相当的性能。Snorkel 在众多领域具有适用性。例如，在微生物组、关节置换和癌症等生物医学领域，Snorkel 正被广泛应用。欲了解更多信息或下载，请访问 http://snorkel.stanford.edu。要查看2017年7月研讨会录音、幻灯片和其他材料，请点击“下载”。

本项目包括以下软件/数据包：

<ul>
<li><a href="https://simtk.org/frs?group_id=1263#pack_2060">Snorkel 研讨会（2018年11月）</a>：2018年11月Snorkel 研讨会的材料。</li>
<li><a href="https://simtk.org/frs?group_id=1263#pack_1963">Snorkel 研讨会（2017年7月）</a>：2017年7月Snorkel 研讨会的材料。</li>
</ul>