We discuss the application of recursive neural networks to domains with recursive structure and describe our attempts to build a model capable of matching sentence pairs and, by extension, of finding the answer that most corresponds to some given question. Our early results are poor, but they indicate that our model is correct and can be competitive given enough time and data.

The SL synchronous programming model is a relaxation of the Esterel synchronous model where the reaction to the absence of a signal within an instant can only happen at the next instant. In previous work, we have revisited the SL synchronous programming model. In particular, we have discussed an alternative design of the model including thread spawning and recursive definitions, introduced a CP...

We discuss resource-bounded measures on the class of recursive structures and prove that with respect to such measures a random recursive structure is almost surely isomorphic to the unique countable model of the extension axioms.