NERD meets NIF: Lifting NLP extraction results to the linked data cloud

We have often heard that data is the new oil. In particular, extracting information from semi-structured textual documents on the Web is key to realize the Linked Data vision. Several attempts have been proposed to extract knowledge from textual documents, extracting named entities, classifying them according to pre-defined taxonomies and disambiguating them through URIs identifying real world entities. As a step towards interconnecting the Web of documents via those entities, different extractors have been proposed. Although they share the same main purpose (extracting named entity), they differ from numerous aspects such as their underlying dictionary or ability to disambiguate entities. We have developed NERD, an API and a front-end user interface powered by an ontology to unify various named entity extractors. The unified result output is serialized in RDF according to the NIF specification and published back on the Linked Data cloud. We evaluated NERD with a dataset composed of five TED talk transcripts, a dataset composed of 1000 New York Times articles and a dataset composed of the 217 abstracts of the papers published at WWW 2011.