On the rules given to lms programs using artificial intelligence with the help of natural language processing

---

 
A PROGRAM THAT AUTOMATICALLY CREATES QUESTIONS BASED 
ON THE RULES GIVEN TO LMS PROGRAMS USING ARTIFICIAL 
INTELLIGENCE WITH THE HELP OF NATURAL LANGUAGE 
PROCESSING. 
Department of Engineering & Technology 
MASTER OF SCIENCE 
in Computer Science & Engineering 

---

Annotation 
This thesis suggests a novel rule-based method for automatically generating 
questions. The suggested method focuses on analyzing a sentence's syntactic and 
semantic structure. Additionally, a thorough explanation of the suggested approach's 
design and execution is provided. Although question generation from sentences is 
the designed system's primary goal, automatic evaluation results show that it also 
performs admirably on reading comprehension datasets that place more emphasis on 
question generation from paragraphs. The designed system significantly 
outperforms all other systems when evaluated by humans and produces the most 
natural (human-like) questions. If high-quality questions can be successfully 
generated, its possible application could be: 
• Help to automatically generate simple questions for reading comprehension test. 
• Help generate more data for QA datasets. 
• Help to train the QA model in a semi-supervised manner. 
KEY WORDS: Natural Language Processing (NLP), Natural Language 
Understanding (NLU), Natural Language Generation (NLG), Automating-
question, Question Answering (QA). 

---

Introduction 
Artificial intelligence (AI) has a subfield called Natural Language Processing 
(NLP). Although there are some differences, the research in this area focuses on 
natural language, which is the language that people use on a daily basis. As a result, 
it is closely tied to linguistics research. NLP is not a broad study of natural language; 
rather, it is the creation of computer systems, particularly software systems, that can 
successfully communicate in natural language. As soon as natural language 
communication between humans and computers is realized, the computer will be 
able to convey specific thoughts and intentions as well as understand the meaning 
of natural language texts. Natural Language Understanding (NLU) refers to the first, 
and Natural Language Generation to the second (NLG). 
An essential component of the Natural Language Processing (NLP) or, more 
specifically, the Natural Language Understanding (NLU) discipline is the question-
answering (QA) task. We presume a computer has a certain level of knowledge if it 
can respond to inquiries about a certain corpus after "reading" it by simulating the 
reading comprehension exam. The rapid creation of models with good performance 
on various well-known QA datasets over the past few years has been seen. Some of 
these models even outperform human performance. In this degree project, we would 
like to reverse the process and produce questions given the answers and 
accompanying material, as opposed to further creating the model for the QA work. 
The questions should, to some extent, represent the understanding of the 
corpus since the design of the QA task seeks to test the machine's capacity for 
reading comprehension. Since the question cannot be simply extracted from the text, 
this project additionally incorporates Natural Language Generation (NLG), in 
addition to the NLU component. 

---