Published April 26, 2022 | Version v1.0.0
Software Open

LinkingPark: Automatic Semantic Table Interpretation Software

  • 1. Microsoft Research Asia, HIT
  • 2. Microsoft Research Cambridge
  • 3. Microsoft Research Asia
  • 4. HIT

Description

LinkingPark is an open-sourced system for automatic semantic table interpretation. Given a table of data, the system can match tabular elements to existing knowledge graphs (in this release, primarily Wikidata). Such semantic information from tabular data can then empower various downstream applications, e.g., intelligent spreadsheet programs, knowledge base population, data integration and cleaning, etc.
LinkinkingPark is unsupervised, stand-alone, and also provides flexibility for multilingual support out of the box.
This initial public release builds on top of the previous internal version that won 2nd prize in the SemTab 2020 competition and provides much improved efficiency and stability while maintaining or improving correctness over different datasets.

Notes

LinkingPark is available on GitHub: https://github.com/microsoft/vert-papers/tree/master/papers/LinkingPark. Contributions and collaboration are welcome.

Files

LinkingPark-public-v1.0.0.zip

Files (111.8 kB)

Name Size Download all
md5:047b1df40854a2a17190d39ef297f1bf
111.8 kB Preview Download

Additional details