Все выпуски

Intent detection plays a crucial role in task-oriented conversational systems. To understand the user’s goal, the system relies on its intent detector to classify the user’s utterance, which may be expressed in different forms of natural language, into intent classes. However, lack of data, and the efficacy of intent detection systems has been hindered by the fact that the user’s intent text is typically characterized by short, general sentences and colloquial expressions. The process of algorithmically determining user intent from a given statement is known as intent detection. The goal of this study is to develop an intent detection model that will accurately classify and detect user intent. The model calculates the similarity score of the three models used to determine their similarities. The proposed model uses Contextual Semantic Search (CSS) capabilities for semantic search, Latent Dirichlet Allocation (LDA) for topic modeling, the Bidirectional Encoder Representations from Transformers (BERT) semantic matching technique, and the combination of LDA and BERT for text classification and detection. The dataset acquired is from the broad twitter corpus (BTC) and comprises various meta data. To prepare the data for analysis, a pre-processing step was applied. A sample of 1432 instances were selected out of the 5000 available datasets because manual annotation is required and could be time-consuming. To compare the performance of the model with the existing model, the similarity scores, precision, recall, f1 score, and accuracy were computed. The results revealed that LDA-BERT achieved an accuracy of 95.88% for intent detection, BERT with an accuracy of 93.84%, and LDA with an accuracy of 92.23%. This shows that LDA-BERT performs better than other models. It is hoped that the novel model will aid in ensuring information security and social media intelligence. For future work, an unsupervised LDA-BERT without any labeled data can be studied with the model.

Intent detection plays a crucial role in task-oriented conversational systems. To understand the user’s goal, the system relies on its intent detector to classify the user’s utterance, which may be expressed in different forms of natural language, into intent classes. However, lack of data, and the efficacy of intent detection systems has been hindered by the fact that the user’s intent text is typically characterized by short, general sentences and colloquial expressions. The process of algorithmically determining user intent from a given statement is known as intent detection. The goal of this study is to develop an intent detection model that will accurately classify and detect user intent. The model calculates the similarity score of the three models used to determine their similarities. The proposed model uses Contextual Semantic Search (CSS) capabilities for semantic search, Latent Dirichlet Allocation (LDA) for topic modeling, the Bidirectional Encoder Representations from Transformers (BERT) semantic matching technique, and the combination of LDA and BERT for text classification and detection. The dataset acquired is from the broad twitter corpus (BTC) and comprises various meta data. To prepare the data for analysis, a pre-processing step was applied. A sample of 1432 instances were selected out of the 5000 available datasets because manual annotation is required and could be time-consuming. To compare the performance of the model with the existing model, the similarity scores, precision, recall, f1 score, and accuracy were computed. The results revealed that LDA-BERT achieved an accuracy of 95.88% for intent detection, BERT with an accuracy of 93.84%, and LDA with an accuracy of 92.23%. This shows that LDA-BERT performs better than other models. It is hoped that the novel model will aid in ensuring information security and social media intelligence. For future work, an unsupervised LDA-BERT without any labeled data can be studied with the model.

WS-BPEL — это широко распространённый стандарт для спецификации распределенных и параллельных бизнес-процессов. Этот стандарт не подходит для алгебраических парадигм и парадигм направленных графов Петри. Исходя из этого, легко определить бизнес-процесс WS-BPEL с нежелательными особенностями. Именно поэтому проверка бизнес-процессов WS-BPEL очень важна. Цель этой статьи состоит в том, чтобы показать некоторые возможности для преобразования процессов WS-BPEL в более формальные спецификации, которые могут быть проверены. CSP и система обозначений Z используются как формальные модели. Система обозначений Z полезна для спецификации абстрактных типов данных. Web-сервисы могут рассматриваться как своего рода абстрактные типы данных.

WS-BPEL is a widely accepted standard for specification of business distributed and parallel processes. This standard is a mismatch of algebraic and Petri net paradigms. Following that, it is easy to specify WS-BPEL business process with unwanted features. That is why the verification of WS-BPEL business processes is very important. The intent of this paper is to show some possibilities for conversion of a WS-BPEL processes into more formal specifications that can be verified. CSP and Z-notation are used as formal models. Z-notation is useful for specification of abstract data types. Web services can be viewed as a kind of abstract data types.

В работе приведены результаты исследований по созданию математической модели морального выбора, основанной на развитии подхода, предложенного В.А. Лефевром. В отличие от В.А. Лефевра, который рассматривал весьма умозрительную ситуацию морального выбора субъекта между абстрактными добром и злом под давлением на него внешнего мира с учетом субъективного восприятия субъектом этого давления, в нашем исследовании рассмотрена более приземленная и практически значимая ситуация. Рассматривается случай, когда субъект при принятии решений ориентируется на свое индивидуальное восприятие внешнего мира (которое может быть искаженным, например, вследствие внешнего целенаправленного информационного воздействия на субъекта и манипулирования его сознанием), а добро и зло не абстрактны, а обусловлены системой ценностей, принятой в конкретном рассматриваемом обществе и привязанной к конкретной идеологии/религии, которые могут быть различными для разных обществ.

В результате проведенных исследований разработана базовая математическая модель, рассмотрены частные случаи ее применения. Выявлены некоторые закономерности, связанные с моральным выбором, приведено их формальное описание. В частности, на языке модели рассмотрена ситуация манипулирования сознанием, сформулирован закон снижения моральности общества, состоящего из так называемых свободных субъектов (то есть таких, которые стремятся действовать в соответствии со своими интенциями и соответствовать в своих действиях образу своего «я»).

The paper presents the results of research on the creation of a mathematical model of moral choice based on the development of the approach proposed by V. A. Lefebvre. Unlike V. A. Lefebvre, who considered a very speculative situation of a subject’s moral choice between abstract “good” and “evil” under pressure from the outside world, taking into account the subjective perception of this pressure by the subject, our study considers a more mundane and practically significant situation. The case is considered when the subject, when making decisions, is guided by his individual perception of the outside world (which may be distorted, for example, due to external purposeful informational influence on the subject and manipulation of his consciousness), and “good” and “evil” are not abstract, but are conditioned by a value system adopted in a particular society under consideration and tied to a specific ideology/religion, which may be different for different societies.

As a result of the conducted research, a basic mathematical model has been developed, and special cases of its application have been considered. Some patterns related to moral choice are revealed, and their formal description is given. In particular, the situation of manipulation of consciousness is considered in the language of the model, the law of reducing the “morality” of a society consisting of so-called free subjects (that is, those who strive to act in accordance with their intentions and correspond in their actions to the image of their “I”) is formulated.