A neural parser is described that computes sentence structure and achieves compositionality in a simple and effective way. The model is compositional in the sense that it is able to analyze new structures-never having been seen before -which are recursive combinations of known structures. The model's performance is compared to a recently proposed neural parser [6] in terms of efficiency and computational capacity. To test the efficiency of the model we ran two groups of experiments. In the first group, we used the same training and test sentences as did Mikkulainen [6]. We also carried out experiments using smaller training sets and we considerably increased the size of the vocabulary used by Mikkulainen. In the second group of experiments, we used real texts (WSJ Penn Tree Bank II) [4] and integrated the parser with a syntactic disambiguation system ([10] and [1]) as well as a semantic disambiguation system [11]. The objective of the second group of experiments was to maximize the compositionality; that from the simplest training set possible-made up of a reduced number of simple expressions-the maximum number of complex sentences could be analyzed in the test phase. The results were very promising.