Want a program that can create thousands of new sentences that are grammatically correct - and - semantically relevant.
Though you should suggest what you think is good idea or not then I assume the following approach would be a feasible idea:
1) program gets input file 1 (with 5 or 50 MB of text) with general text sentence that program learns the "grammar" from by using statistics of how often a word occurs before or after 2 or 3 word.
2) Input file 2 contains text sentences that is "semantically relevant" (this txt file is much smaller, say, 200 kb)
3) input txt file 3 contains specific words or phrases (1 per line) so the program knows what words from the input file 2 that the program should look for to merge these words into the output sentences that the program makes.
Before the very first use then a function is used so program calculates the statistics of occurence for inpout file #1. This is done only 1 time (unless file is changed) for words/phrases with 2, 3 and 4 words.
Program then makes user-specified XX number of sentences that are new and are gramatically and semantically correct. Each sentence must be between 9-20 words.
Program makes output file in real time and show many sentences it has made so far.
Write what experience you have with similar programs and your background as well as why you are the right coder for this bid.
IMPORTANT: All sentences made must be "grammatically correct" in Microsoft Word when using "spelling and grammar"-checker function in Microsoft Word.
1) Complete and fully-functional working program(s) in executable form as well as complete source code of all work done.
2) Deliverables must be in ready-to-run condition, as follows (depending on the nature of the deliverables):
a) For web sites or other server-side deliverables intended to only ever exist in one place in the Buyer's environment--Deliverables must be installed by the Seller in ready-to-run condition in the Buyer's environment.
b) For all others including desktop software or software the buyer intends to distribute: A software installation package that will install the software in ready-to-run condition on the platform(s) specified in this bid request.
3) All deliverables will be considered "work made for hire" under U.S. Copyright law. Buyer will receive exclusive and complete copyrights to all work purchased. (No GPL, GNU, 3rd party components, etc. unless all copyright ramifications are explained AND AGREED TO by the buyer on the site per the coder's Seller Legal Agreement).
perl or .net