sling-20190320


  • The sling project is still work in progress. We do not yet have a full system that can extract facts from arbitrary text, but we have built a number of the subsystems needed for such a system. The sling frame store is our basic framework for building and manipulating frame semantic graph structures. The [Wiki flow pipeline](doc/guide/wikiflow.md) can take a raw dump of Wikidata and [convert](doc/guide/wikiflow.md#wikidata-import) this into one big frame graph. This can be loaded into memory so we can do fast graph traversal for inference and reasoning over the knowledge base. The Wiki flow pipeline can also take raw Wikipedia dumps and [convert](doc/guide/wikiflow.md#wikipedia-import-and-parsing) these into a set of documents with structured annotations extracted from the Wiki markup. This also produces [phrase tables](doc/guide/wikiflow.md#name-and-phrase-tables) that are used for mapping names to entities. There is a [sling Python api](doc/guide/pyapi.md) for accessing all this information and we also have a [bot](python/wikibot) for uploading extracted facts to Wikidata.