Automated Summarization of Bug Reports to speed-up software development/maintenance process by using Natural Language Processing (NLP)

Author(s):  
M. Irtaza Nawaz Tarar ◽  
Faizan Ahmed ◽  
Wasi Haider Butt

The software development procedure begins with identifying the requirement analysis. The process levels of the requirements start from analysing the requirements to sketch the design of the program, which is very critical work for programmers and software engineers. Moreover, many errors will happen during the requirement analysis cycle transferring to other stages, which leads to the high cost of the process more than the initial specified process. The reason behind this is because of the specifications of software requirements created in the natural language. To minimize these errors, we can transfer the software requirements to the computerized form by the UML diagram. To overcome this, a device has been designed, which plans can provide semi-automatized aid for designers to provide UML class version from software program specifications using natural Language Processing techniques. The proposed technique outlines the class diagram in a well-known configuration and additionally facts out the relationship between instructions. In this research, we propose to enhance the procedure of producing the UML diagrams by utilizing the Natural Language, which will help the software development to analyze the software requirements with fewer errors and efficient way. The proposed approach will use the parser analyze and Part of Speech (POS) tagger to analyze the user requirements entered by the user in the English language. Then, extract the verbs and phrases, etc. in the user text. The obtained results showed that the proposed method got better results in comparison with other methods published in the literature. The proposed method gave a better analysis of the given requirements and better diagrams presentation, which can help the software engineers. Key words: Part of Speech,UM


2020 ◽  
pp. 3-17
Author(s):  
Peter Nabende

Natural Language Processing for under-resourced languages is now a mainstream research area. However, there are limited studies on Natural Language Processing applications for many indigenous East African languages. As a contribution to covering the current gap of knowledge, this paper focuses on evaluating the application of well-established machine translation methods for one heavily under-resourced indigenous East African language called Lumasaaba. Specifically, we review the most common machine translation methods in the context of Lumasaaba including both rule-based and data-driven methods. Then we apply a state of the art data-driven machine translation method to learn models for automating translation between Lumasaaba and English using a very limited data set of parallel sentences. Automatic evaluation results show that a transformer-based Neural Machine Translation model architecture leads to consistently better BLEU scores than the recurrent neural network-based models. Moreover, the automatically generated translations can be comprehended to a reasonable extent and are usually associated with the source language input.


Sign in / Sign up

Export Citation Format

Share Document