Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Electronic archive o...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Генерация текста на основе цепей Маркова для чат-бота

Генерация текста на основе цепей Маркова для чат-бота

Abstract

В работе рассмотрена математическая модель для интеллектуальной генерации текста для чат-бота. С использованием сервиса DialogFlow Google мы разработали чат-бот TPU_VKR. Для обучения чат-бота мы создали корпус вопросов-ответов, затем разработали сценарий ведения диалога в зависимости от выбора пользователя. С использованием API DialogFlow Google на языке Python были выгружены диалоги, которые стали основой для интеллектуальной генерации текста с использованием цепей Маркова. Для определения семантического сходства между фразами мы использовали косинусное расстояние. Результаты расчетов показали, что косинусное расстояние между оригинальной фразой и сгенерированными фразами лежит в пределах 0,44 от 0,96.

The paper considers a mathematical model for intelligent generation of text for a chat bot. Using the DialogFlow Google service, we have developed the TPU_VKR chatbot. To train the chat bot, we created a corpus of questions and answers, then developed a script for conducting a dialogue, depending on the user's choice. Using the Google DialogFlow API in Python, dialogs were unloaded, which became the basis for intelligent text generation using Markov chains. We used cosine distance to determine the semantic similarity between phrases. The calculation results showed that the cosine distance between the original phrase and the generated phrases is within the range of 0.44 from 0.96.

Country
Russian Federation
Related Organizations
Keywords

обработка естественного языка, 004.773.6:519.876, Markov chains, система сквозной разработки, end-to-end development system, чат-боты, 519.876 [004.773.6], цепи Маркова, математические модели, сhat-bot, natural language processing, mathematical models, 01.04.02

  • BIP!
    Impact byBIP!
    citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
  • citations
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
    Powered byBIP!BIP!
Powered by OpenAIRE graph
Found an issue? Give us feedback
citations
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Related to Research communities
Digital Humanities and Cultural Heritage