A graph digital signal processing method for semantic analysis

This paper focuses on the problem of devising a computationally tractable procedure for representing the natural language understanding (NLU). It approaches this goal, by using distributional models of meaning through a method from graph-based digital signal processing (DSP) which only recently grabbed the attention of researchers from the field of natural language processing (NLP) related to big data analysis. The novelty of our approach lies in the combination of three domains: advances in deep learning algorithms for word representation, dependency parsing for modeling inter-word relations and convolution using orthogonal Hadamard codes for composing the two previous areas, generating a unique representation for the sentence. Two types of problems are resolved in a new unified way: sentence similarity given by the cos function of the corresponding vectors and question-answering where the query is matched to possible answers. This technique resembles the spread spectrum methods from telecommunication theory where multiple users share a common channel, and are able to communicate without interference. In the content of this paper the case of individual words play the role of users sharing the same sentence. Examples of the method application to a standard set of sentences, used for benchmarking the accuracy and the execution time is also given.