• Using Wikipedia and Wikidata for Natural Language Processing

    WeWork Coworking & Office Space

    Our March speaker is Gabriel Altay from Kensho (https://www.kensho.com/), speaking on Using Wikipedia and Wikidata for NLP. We'll be meeting again at WeWork Navy Yard. Doors open at 6 pm for networking and refreshments courtesy of Kensho -- thanks! -- and our program starts at 6:30 pm. Gabriel's talk description: Wikipedia (the free encyclopedia) and Wikidata (the free knowledge base) are crowd sourced projects supported by the Wikimedia Foundation. In addition to being great resources for knowledge sharing, they are excellent laboratories for research into natural language processing (NLP). During the first part of this talk, Gabriel will introduce a derived dataset put together by the Kensho (https://www.kensho.com) R&D group for NLP. Read more about the dataset at https://blog.kensho.com/announcing-the-kensho-derived-wikimedia-dataset-5d1197d72bcf. In the second half of the talk he will show some example use cases including named entity disambiguation, entity graph embedding, and explicit topic modeling. Bio: Gabriel used to be an astronomer but is now a machine learning engineer at Kensho focusing on natural language processing.