Mimic learns to speak solely by talking to others. He has no defined rules and knows nothing about the language. His database started completely empty (and he was less fun to talk to then).

Mimic works by creating a pattern based on a tokenized version of a limited number of the most recent things said in the conversation.

When you say something to him, Mimic figures out what to say by finding the closest match from the database for the pattern consisting of what you said, what he said, and a small bit of context. A typical pattern might look like:

how you qq|doing great|what up qq|Well not much, just talking to you.

If this were the pattern matched, Mimic would return "Well not much, just talking to you."

I had been toying abstractly with the idea of a similar bot for years, but the design for Mimic came to me in a dream three years ago and has remained virtually unchanged since. Mimic could benefit greatly from a good pattern promotion/demotion scheme and a pruning mechanism.

Roughly the idea behind mimic is adapted from a concept called Associative Pattern Retrieval by Robert A. Levinson at the University of California, Santa Cruz. (more: lite & heavy)

Back to Mimic