Проблемы обработки естественного языка в диалоговых системах

Системный администратор. 2019. № 10. С. 82–91.

Klyshinskiy E., Жеребцова Ю., Чижик А.

Nowadays, a field of dialogue systems and conversational agents is one of the rapidly growing research areas in artificial intelligence applications. Business and industry are showing increasing interest in implementing intelligent conversational agents into their products. Many recent studies has tended to focus on possibility of developing task-oriented systems which are able to have long and free social chats that occur naturally in social human interactions. In order to better understand the user’s expression, and then feedback the correct information, natural language understanding plays an extremely important role. Despite progress made in solving NLP problems, it remains very challenging today in the field of dialogue systems. In this paper, we review the recent progress in developing dialogue systems, its current architecture features and further prospects. We focus on the natural language understanding tasks which are key for building a good conversational agent, and than we are summarizing NLP methods and frameworks, in order to allow researchers to study the potential improvements of the state-of-the-art dialogue systems. Additionally, we consider the dialogue concept in context of human-machine interaction, and briefly describe dialogue evaluation metrics.

Keywords: искусственный интеллект, компьютерная лингвистика, natural language processing, computational linguistics, обработка естественного языка, интеллектуальный агент, natural language interface, чат-бот, диалоговая система, Natural Language Understanding, dialogue systems, conversational agent, intelligent personal assistant