Hi James, Your web site is informative. I very much seek comments, input and collaboration with the AI Lab at the University of Texas. I see that your interest is knowledge based systems. I worked indirectly with Dr. Porter during my tenure at Cycorp as its first manager for the DARPA Rapid Knowledge Formation project, which is strongly influencing my current project stage.
The design of the Texai bootstrap dialog system is published on my blog: http://texai.org/blog/2008/01/20/bootstrap-dialog-system-design and I am keeping that documentation up to date as I write the code. At the moment I am working on the developer's chat interface, which resembles a client for instant messaging. This is the node labeled UI console chat session node in my illustration. Pre-released source code is stored in the project's SourceForge repository which can be browsed at: http://texai.svn.sourceforge.net/viewvc/texai . The Incremental Fluid Construction Grammar grammar rule application libraries are done, except for heuristics to choose the best rules out of the multitude that I think will be eventually present. All skills on the diagram remain to be written, but I expect the code volume to be reasonable given that this is a bootstrap system. It would honor me greatly to present my work to you and any of your fellows at UT. I am developing a talk to give to my former coworkers at Cycorp soon. The Fifth International Conference on Construction Grammar is to be held at UT, September 26, 2008. I have submitted this abstract, and if it is accepted then I'll write the associated paper. The research is already completed and briefly summarized in my blog. Furthermore I edited the Wikipedia article on FCG to explain more about how it works. A cognitively-plausible implementation of Fluid Construction Grammar (FCG) is described in which the grammar rules are adopted from Double R Grammar (DRG). FCG provides a bi-directional rule application engine in which the working memory is a coupled semantic and syntactic feature structure. FCG itself does not commit to any particular lexical categories, nor does it commit to any particular organization of construction rules. DRG, previously implemented in the ACT-R cognitive architecture, is a linguistic theory of the grammatical encoding and integration of referential and relational meaning in English. Its referential and relational constructions facilitate the composition of logical forms. In this work, a set of bi-directional FCG rules are developed that comply with DRG. Results demonstrate both the lexically incremental parse of an utterance to precise, discourse-referential, logical form, and the semantically incremental production of the original utterance, given as input the discourse-grounded logical form. Lets's keep in touch. -Steve Stephen L. Reed Artificial Intelligence Researcher http://texai.org/blog http://texai.org 3008 Oak Crest Ave. Austin, Texas, USA 78704 512.791.7860 ----- Original Message ---- From: James Ratcliff <[EMAIL PROTECTED]> To: [email protected] Sent: Wednesday, January 23, 2008 11:55:19 AM Subject: Re: [agi] Incremental Fluid Construction Grammar released I agree with most everything you have said so far, is in line with alot of the thoughts I have had. How far along is your dialog system? I am here in Austin as well, and would be interested in talking with you further as time permits. James _______________________________________ James Ratcliff - http://falazar.com Looking for something... Never miss a thing. Make Yahoo your homepage. This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?&; ____________________________________________________________________________________ Be a better friend, newshound, and know-it-all with Yahoo! Mobile. Try it now. http://mobile.yahoo.com/;_ylt=Ahu06i62sR8HDtDypao8Wcj9tAcJ ----- This list is sponsored by AGIRI: http://www.agiri.org/email To unsubscribe or change your options, please go to: http://v2.listbox.com/member/?member_id=8660244&id_secret=89104221-dd2b8c
