The paper introduces a recursive neural network (RNN) model that learns compositional vector representations for phrases and sentences of arbitrary syntactic type and length. The model assigns a vector and a matrix to each node in a parse tree, where the vector captures the inherent meaning of the constituent, and the matrix captures how it changes the meaning of neighboring words or phrases. This matrix-vector RNN can learn the meaning of operators in propositional logic and natural language, achieving state-of-the-art performance on various tasks such as predicting fine-grained sentiment distributions of adverb-adjective pairs, classifying sentiment labels of movie reviews, and classifying semantic relationships between nouns using the syntactic path between them. The model's ability to capture semantic compositionality in a syntactically plausible way is demonstrated through experiments, showing its effectiveness in handling complex linguistic phenomena.The paper introduces a recursive neural network (RNN) model that learns compositional vector representations for phrases and sentences of arbitrary syntactic type and length. The model assigns a vector and a matrix to each node in a parse tree, where the vector captures the inherent meaning of the constituent, and the matrix captures how it changes the meaning of neighboring words or phrases. This matrix-vector RNN can learn the meaning of operators in propositional logic and natural language, achieving state-of-the-art performance on various tasks such as predicting fine-grained sentiment distributions of adverb-adjective pairs, classifying sentiment labels of movie reviews, and classifying semantic relationships between nouns using the syntactic path between them. The model's ability to capture semantic compositionality in a syntactically plausible way is demonstrated through experiments, showing its effectiveness in handling complex linguistic phenomena.