利用五亿条开放协作记录关联组织数据集
Linking Datasets on Organizations Using Half A Billion Open-Collaborated Records
AI总结：
本文利用LinkedIn五亿条开放协作记录构建大规模训练语料库，通过引入数万亿名称对示例改进组织名称模糊匹配的校准与性能，并开源全部数据和方法。
摘要：
研究组织问题的学者经常需要处理多个缺乏共享标识符或协变量的数据集。在这种情况下，研究人员通常使用近似字符串（“模糊”）匹配方法来合并数据集。字符串匹配虽然有用，但面临根本性挑战。即使两个字符串在人类看来相似，模糊匹配也常常难以胜任，因为它无法适应字符组合的信息量。为此，人们开发了多种机器学习方法来改进字符串匹配。然而，这些方法的有效性受到训练数据规模和多样性的限制。本文引入来自一个知名职业社交网站（LinkedIn）的数据作为大规模训练语料库，以解决这些局限性。通过利用LinkedIn语料库中关于组织名称到名称链接的信息，我们将数万亿个名称对示例纳入各种方法中，通过显式最大化匹配概率来增强现有匹配基准和性能。我们还展示了如何使用LinkedIn数据的网络表示来建模组织名称之间的关系。在涉及游说公司的示例性合并任务中，我们记录了在匹配校准中使用LinkedIn语料库所带来的改进，并将所有数据和方法开源。
英文摘要：
Scholars studying organizations often work with multiple datasets lacking shared identifiers or covariates. In such situations, researchers usually use approximate string ("fuzzy") matching methods to combine datasets. String matching, although useful, faces fundamental challenges. Even where two strings appear similar to humans, fuzzy matching often struggles because it fails to adapt to the informativeness of the character combinations. In response, a number of machine learning methods have been developed to refine string matching. Yet, the effectiveness of these methods is limited by the size and diversity of training data. This paper introduces data from a prominent employment networking site (LinkedIn) as a massive training corpus to address these limitations. By leveraging information from the LinkedIn corpus regarding organizational name-to-name links, we incorporate trillions of name pair examples into various methods to enhance existing matching benchmarks and performance by explicitly maximizing match probabilities. We also show how relationships between organization names can be modeled using a network representation of the LinkedIn data. In illustrative merging tasks involving lobbying firms, we document improvements when using the LinkedIn corpus in matching calibration and make all data and methods open source.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
