Thompson/Reuters provides a free web-service OpenCalais that can be used for information extraction from unstructured text/html/xml documents. It can recognize not only named entities, but also facts and events. There is a Python interface available to this Web service called python-calais.
skip to main |
skip to sidebar
My study of machine learning, data mining, computational linguistics and information retrieval, towards the grand goal of developing the "perfect search engine" that "understands exactly what you mean and gives you back exactly what you want" (Larry Page).
Posts
No comments:
Post a Comment