Conference Presentations by Senthilkumar P
Emerging Trends, 2023
Automatic question generation refers to the idea of creating questions automatically from the tex... more Automatic question generation refers to the idea of creating questions automatically from the text provided rather than
manually creating questions for the student evaluation technique. The six stages of AQG are text pre-processing,
sentence selection, keyword selection, distractors selection, question framing, and post processing. Distractors are one of
the six phases of AQG that are utilised in multiple choice question generation, and they are crucial in determining how
challenging the questions will be.
In our suggested strategy, we focus the selection of the distractors and suggest a novel hybridised model technique for
producing distractor to the MCQ type questions. This approach of selecting distractions involves three steps: first,
gathering distractions from wordnet, conceptnet, and sense2vec; second, structuring questions with these distractions;
and third, scoring the sentence with the aid of the word closeness concept.
Based on the scoring, we choose the top n sentences from the framed sentence, and the best distractor is chosen from the
top n selected sentences. When compared to the performance of wordnet, conceptnet, and sence2vec individually, this
technique outperforms them all in terms of the overall selection of better distractions selection, accuracy and question
quality.
RTCS 2023, 2023
Manually creating questions from the text is a complex process, and designing the questions so th... more Manually creating questions from the text is a complex process, and designing the questions so that all levels of ability may be tested is even more challenging. Manually writing questions demands a person with knowledge of the context and some writing experience. The most important thing is that it should consume lot of our time. Automatic Question Generation [AQG] is a theory that we use to help us solve the problem of framing questions and the textual content is used as the input for AQG, and questions are produced as the output. We use Bloom's Taxonomy Scale approach to solve another challenging task of setting up a question paper for checking all the cognitive skill levels, this scale determines the difficulty level of the questions and can be used to test all the student's cognitive abilities. Bloom's Taxonomy has six cognitive levels, mapped with the six types of AQG classifications. Each stage of Bloom's Taxonomy has different difficulties, and we can use this method from primary school to higher education. Furthermore, we can adjust the question paper according to the situation and the student's needs, and it gives a variety of questions with varying difficulty levels. It is a complete package of well-framed, automated question papers to check students' abilities at all levels. This method allows us a good amount of flexibility when it comes to producing automated test questions that can measure all cognitive skill levels.
Tamil Internet Conference 2022, 2022
The main objective of an assessment is to measure student's learning abilities and increase such ... more The main objective of an assessment is to measure student's learning abilities and increase such abilities by correcting them in line with their knowledge. Question generation plays a vital role in assessment, The creation of the questions for the assessment is a challenging task, and manually creating a question is a complicated operation that requires expertise, knowledge, and, most importantly, it is a time-consuming process. Automatic question generation (AQG) is a savior to overcome these issues. AQG comprises of six critical stages, with keyword selection being the most significant stage and a crucial component of question quality. Therefore, we focus on the keyword selection method and propose a novel method for automatically extracting keywords from Tamil text to generate questions in Tamil. This keyword selection process involves two important concepts; the first focuses on how significant a keyword is depending on web-based search results and the notable information it contains, the secondfocuses on giving a keyword weight depending on how frequently it appears and how it is distributed in the corpus. The keyword selection method performs significantly better for Tamil-based question generation when compared to certain other keyword selection techniques in terms of accuracy and question quality.
Uploads
Conference Presentations by Senthilkumar P
manually creating questions for the student evaluation technique. The six stages of AQG are text pre-processing,
sentence selection, keyword selection, distractors selection, question framing, and post processing. Distractors are one of
the six phases of AQG that are utilised in multiple choice question generation, and they are crucial in determining how
challenging the questions will be.
In our suggested strategy, we focus the selection of the distractors and suggest a novel hybridised model technique for
producing distractor to the MCQ type questions. This approach of selecting distractions involves three steps: first,
gathering distractions from wordnet, conceptnet, and sense2vec; second, structuring questions with these distractions;
and third, scoring the sentence with the aid of the word closeness concept.
Based on the scoring, we choose the top n sentences from the framed sentence, and the best distractor is chosen from the
top n selected sentences. When compared to the performance of wordnet, conceptnet, and sence2vec individually, this
technique outperforms them all in terms of the overall selection of better distractions selection, accuracy and question
quality.