home.social

#recordlinkage — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #recordlinkage, aggregated by home.social.

  1. From the abstract:

    ›We also select an unsupervised state-of-the-art matcher from the field of #DeepLearning for a thorough comparison.

    Our results show that neither #AutoCal nor the state-of-the-art matcher is superior regarding matching quality while AutoCal has only moderate hardware requirements and runs 2.7 to 60 times faster.‹

    3/4

    🌺

    🏷️ #InstanceMatching #RecordLinkage #OntologyMatching #ArtificialIntelligence #MatChain #PyPI #WorldAvatar #DigitalTwin #WebSem #LinkedData #KnowledgeGraph

  2. From the abstract:

    ›We introduce #AutoCal, a new #InstanceMatcher which does not require #LabelledData and runs out of the box for a wide range of domains without tuning method-specific parameters.

    AutoCal achieves results competitive to recently proposed unsupervised matchers from the field of #MachineLearning.‹

    2/4

    🌺

    🏷️ #InstanceMatching #RecordLinkage #OntologyMatching #ArtificialIntelligence #MatChain #PyPI #WorldAvatar #DigitalTwin #Python #WebSem #LinkedData #KnowledgeGraph

  3. Commonly used methods for linking CPS ASEC files do not address how to link the ASEC oversample records across years, leading to smaller linked sample sizes. A new paper demonstrates how to recover the linkable oversample cases in the 2005-2020 ASEC, resulting in about 150,000 more linked records (30% increase in the overall linked sample size).
    pubmed.ncbi.nlm.nih.gov/382645
    #Data #Statistics #Methods #DataScience #RecordLinkage

  4. heise+ | DB-Management: Datendubletten mit Python entfernen

    Die Beseitigung von Datendubletten erfordert viel Handarbeit. Python bietet einige Bibliotheken und Tools, die helfen, dieses Ärgernis aus Listen zu entfernen.
    DB-Management: Datendubletten mit Python entfernen