Natural language, our use of communications like text and speech and documents to communicate with other people, would be the ideal way to communicate with computers. Yet there are still complexities of its use that are difficult to implement. Today as part of the Cognitive Systems Institute weekly talk series, attended a presentation by Prof Chris Biemann of the University of Darmstadt, that described their work in this area. Here are the slides. Good, brief exposition of the problem and application directions.
Some of this can be explored interactively here: JoBimText :
JoBimText is an open source framework for application of Distributional Semantics using lexicalized features. It is providing a software solution for automatic text expansion using contextualized distributional similarity The project is maintained by the Language Technology group at the TU Darmstadt and IBM Research. .. "
Subscribe to:
Post Comments (Atom)
No comments:
Post a Comment