Open source software for document geolocation parsing, tagging, and resolving.
CLAVIN (Cartographic Location and Vicinity Indexer) is an open source software package for geotagging and geoparsing. It automatically extracts location names from structured and unstructured text and resolves them against a gazetteer to produce data-rich geographic entities. CLAVIN is fast, accurate, and scalable to accommodate big data in the cloud. CLAVIN combines various open source tools with natural language processing (NLP) techniques to extract and resolve geospatial entities while reconciling misspellings, alternate names, and ambiguous references. By enriching documents with structured geodata, CLAVIN enables low-cost, advanced geospatial analytics on massive volumes of text.