Lymphocyte-style word representations

Semantic similarity between words is becoming a generic problem for many applications of computational linguistics and artificial intelligence. Word representation is the most important determination of similarity. Inspired by the analogies between words and lymphocytes, a lymphocyte-style word representation is proposed. The word representation is built on the basis of dependency syntax of sentences and represent word context as head properties and dependent properties of the word. For learning of the representations, a multi-word-agent autonomous learning model (MWAALM) based on an artificial immune system is presented. This research provides a completely new perspective on language and words. The most significant advantages of this research lie in two aspects: the first is that lymphocyte-style word representation can express both similarities and dependency relations between words, the second is that the MWAALM is implemented concisely and has the potential ability of continuous learning since the simulated targets have the ability of adaptation. Lymphocyte-style word representations are evaluated by computing the similarities between words, and experiments are conducted on the Penn Chinese Treebank 5.1. Experimental results indicate that the proposed word representations are effective.