A matrix-vector recurrent unit model for capturing compositional semantics in phrase embeddings

The meaning of a multi-word phrase not only depends on the meaning of its constituent words, but also the rules of composing them to give the so-called compositional semantic. However, many deep learning models for learning compositional semantics target specific NLP tasks such as sentiment classification. Consequently, the word embeddings encode the lexical semantics, the weights of the networks are optimised for the classification task. Such models have no mechanisms to explicitly encode the compositional rules, and hence they are insufficient in capturing the semantics of phrases. We present a novel recurrent computational mechanism that specifically learns the compositionality by encoding the compositional rule of each word into a matrix. The network uses a recurrent architecture to capture the order of words for phrases with various lengths without requiring extra preprocessing such as part-of-speech tagging. The model is thoroughly evaluated on both supervised and unsupervised NLP tasks including phrase similarity, noun-modifier questions, sentiment distribution prediction, and domain specific term identification tasks. We demonstrate that our model consistently outperforms the LSTM and CNN deep learning models, simple algebraic compositions, and other popular baselines on different datasets.