Identifying People and Locations in Text Corpora with NER
September 26 from 2:00-4:00pm in Bass Library, L06
This workshop will introduce participants to Named Entity Recognition (NER), or the process of algorithmically identifying people, locations, corporations, and other classes of nouns in text corpora. We will help users install and run Stanford's flagship CoreNLP (Natural Language Processing) toolkit to identify entities in text files. Participants are encouraged to bring a small collection of documents they want to analyze during this session; sample data will also be available for use.
Windows machines will be available for use, but participants may also work from Mac or Windows laptops, so long as they have administrative control over them.
Instructor: Doug Duhaime