-
77Symbolic connectionism in natural language disambiguationIEEE Transactions on Neural Networks 9 739-755. 1998.Uses connectionism (neural networks) to extract the "gist" of a story in order to represent a context going forward for the disambiguation of incoming words as a text is processed.
-
55The representation of context: Ideas from artificial intelligenceLaw, Probability and Risk 2 191-199. 2003.To move beyond vague platitudes about the importance of context in legal reasoning or natural language understanding, one must take account of ideas from artificial intelligence on how to represent context formally. Work on topics like prior probabilities, the theory-ladenness of observation, encyclopedic knowledge for disambiguation in language translation and pathology test diagnosis has produced a body of knowledge on how to represent context in artificial intelligence applications.
-
124Why Machines Will Never Rule the World – On AI and FaithIrreverend. Faith and Human Affairs. 2023.Transcript of an Interview on the podcast: Irreverend: Faith and Current Affairs.