Mathematical Backgrounds of Intelligent Systems

A generalized dialogue graph construction and visualization based on a corpus of dialogues

P. D. Shtykov, A. G. Dyakonov

Lomonosov Moscow State University, Moscow, Russia

Abstract: A definition of a generalized dialogue graph is proposed to describe the structure of a dialogue in terms of a corpus of homogeneous dialogues. The task of constructing such a graph is relevant in modern conversational artificial intelligence, however, there are few works with meaningful results, often a complete description of the algorithms is not given and the code with the implementation is not published. In the paper, a method for constructing a generalized dialogue graph is proposed, which is implemented in the Python programming language and made publicly available. Experiments were carried out on open data and the results were described.

Keywords: dialogue system, NLP, graph, dialogue graph, clustering, embeddings.

UDC: 519.7

DOI: 10.17223/20710410/59/7