Powered by OpenAIRE graph
Found an issue? Give us feedback
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 Ð¸Ð½Ñ„Ð¾Ñ€Ð¼Ð°Ñ‚Ð¸Ð²Ð½Ñ‹Ñ Ð²Ð¾Ð¿Ñ€Ð¾ÑÐ¾Ð² в информационно Ð°ÑÑÐ¸Ð¼ÐµÑ‚Ñ€Ð¸Ñ‡Ð½Ñ‹Ñ Ð±ÐµÑÐµÐ´Ð°Ñ

выпускная квалификационная работа магистра

Генерация Ð¸Ð½Ñ„Ð¾Ñ€Ð¼Ð°Ñ‚Ð¸Ð²Ð½Ñ‹Ñ Ð²Ð¾Ð¿Ñ€Ð¾ÑÐ¾Ð² в информационно Ð°ÑÑÐ¸Ð¼ÐµÑ‚Ñ€Ð¸Ñ‡Ð½Ñ‹Ñ Ð±ÐµÑÐµÐ´Ð°Ñ

Abstract

В данной дипломной работе изучается генерация вопросов для поиска информации в открытой коммуникации, которая включает в себя сложные проблемы NLP, например, оценку генерации открытого языка и прагматического мышления. Для решения этих проблем предлагаются автоматические метрики для количественной оценки информативности и специфичности вопросов, которые необходимы для эффективной итеративной разработки системы. Был проведен анализ существующих аналогов для понимания основных тенденций разработки и потенциальных плюсов проектируемого программного продукта. Была разработана диалоговая система, способная вычислять обрабатывать входной текст и генерировать прагматически актуальные вопросы для получения новой информации. Предлагаемый метод представляет собой практическую реализацию прагматики в условиях открытого общения за пределами простых эталонных игр.

This thesis work describes the generation for information retrieval in open communication, which includes complex NLP problems such as evaluating open language generation and pragmatic thinking. To solve these problems, automatic metrics are proposed to quantify the informativeness and specificity of questions, which are necessary for effective iterative system development. An analysis of existing analogues was carried out to understand the main development trends and potential advantages of the designed software product. A dialogue system has been developed that can generate pragmatically relevant and specific questions to gain new information about the invisible source of textual knowledge. The proposed method is a practical implementation of pragmatics in the context of open communication outside of simple reference games.

Keywords

Искусственный интеллект, генерация, auto generation, Информация, dialogue systems, диалоговые системы, Вычислительные машины электронные

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    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 by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
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
Upload OA version
Are you the author of this publication? Upload your Open Access version to Zenodo!
It’s fast and easy, just two clicks!