Название: Natural Language Processing for Software Engineering
Автор: Rajesh Kumar Chakrawarti, Ranjana Sikarwar, Sanjaya Kumar Sarangi, Samson Arun Raj Albert Raj
Издательство: Wiley-Scrivener
Год: 2025
Страниц: 525
Язык: английский
Формат: pdf (true)
Размер: 55.5 MB

Discover how Natural Language Processing for Software Engineering can transform your understanding of agile development, equipping you with essential tools and insights to enhance software quality and responsiveness in today’s rapidly changing technological landscape.

The book’s goal is to discuss the most current trends in applying natural language processing (NLP) approaches. It makes the case that these areas will continue to develop and merit contributions. The book focusses on software development that is based on visual modelling, is object-orientated, and is one of the most significant development paradigms today. To reduce issues throughout the documentation process, there are still a few considerations to make. To assist developers in their documentation tasks, a few aids have been developed. To aid with the documentation process, a variety of related tools (such as assistants) may be made using Natural Language Processing (NLP). The book is focused on software development and operation using data mining, informatics, Big Data analytics, Artificial Intelligence (AI), Machine Learning (ML), digital image processing, the Internet of Things (IoT), cloud computing, computer vision, cyber security, Industry 4.0, and health informatics domains.

The fields of text mining and information retrieval were the origins of natural language processing (NLP), which was first developed from those fields. Throughout the years, several applications that are based on artificial intelligence have developed out of its initial domain. Some examples of these applications include machine translation, query expansion, robotic command detection, and many more. The origins of natural language processing (NLP) may be traced back to a variety of disciplines, such as psychology, mathematics, Computer Science, linguistics, computer engineering, electrical and electronic engineering, Artificial Intelligence, robotics, and Computer Science and information. This paper provides a comprehensive analysis of a wide variety of soft computing techniques to Natural Language Processing (NLP).

Text mining is an important branch of data mining that is used to analyze the text data. Text data is any type of data like structured data, unstructured data, and semi-structured data. All types of data are collected from different sources such as multimedia applications, mobile apps, digital systems, etc. These data are beneficial to get a good insight, meaningful results. We use data mining techniques like Support Vector Machine (SVM), Random Forest (RF), Multilayer Perception (MLP), Naive Bayes (NB), etc. to analyze the hidden relationship between data. We use three kinds of data types in text mining.

Software fault prediction serves to improve testing efficiency and software quality by enabling the early discovery of software problems. This is accomplished via improved program quality. In most cases, the procedure of categorizing is used for the purpose of error detection. During the classification process, coding features and other characteristics are used to produce predictions about the potential occurrence of mistakes. Due to the fact that software defect detection is heavily influenced by poor categorization judgments, it is necessary to have an improved decision-making model to anticipate trends by making use of the attributes retrieved from datasets. Through the use of a collection of software failure datasets, these researchers evaluate the performance of the offered techniques in comparison to that of a wide variety of Machine Learning classifiers. Accuracy, balance, area under the curve, false alarm rate, detection rate, or recall rate were some of the performance criteria that were used in the evaluation of the recommended approaches.






ОТСУТСТВУЕТ ССЫЛКА/ НЕ РАБОЧАЯ ССЫЛКА ЕСТЬ РЕШЕНИЕ, ПИШИМ СЮДА!




[related-news] [/related-news]