Automated Question Generator System: A Review

Procedia Computer Science, 2018

With exploding textual data on the internet with e-books, legal documents and products information, it is an opportunity to harness it for applications which can aid human tasks. Developing systems for question generation can be used for making frequently-askedquestions, creating school quiz-es and serve for the purpose of unified AI. Here in this study various encoder decoder architectures for generating questions from text inputs have been explored using Stanford's SQuAD dataset as for training development and test sets and evaluation metrics such as BLEU, ROUGUE and training time were used to compare the effectiveness of the models. The article develops upon the work of current end-to-end system by using gated recurrent unit in place of long short term memory which give similar accuracy but with lesser training time, further it also show the successfully use of a convolution based encoder for this task which gives results comparable to current state of the art system with much lesser training time.

International Journal of Artificial Intelligence in Education

Questioning plays a vital role in education, directing knowledge construction and assessing students’ understanding. However, creating high-level questions requires significant creativity and effort. Automatic question generation is expected to facilitate the generation of not only fluent and relevant but also educationally valuable questions. While rule-based methods are intuitive for short inputs, they struggle with longer and more complex inputs. Neural question generation (NQG) has shown better results in this regard. This review summarizes the advancements in NQG between 2016 and early 2022. The focus is on the development of NQG for educational purposes, including challenges and research opportunities. We found that although NQG can generate fluent and relevant factoid-type questions, few studies focus on education. Specifically, there is limited literature using context in the form of multi-paragraphs, which due to the input limitation of the current deep learning techniques,...

International Journal of Advanced Trends in Computer Science and Engineering, 2020

This research aims to create a system that generates questions that are used in higher education circles. This study uses a machine learning approach is to create questions that refer to the taxonomic bloom. This study also uses encoder-decoder and attention techniques that are used to look for context. The dataset used consisted of 93,000 pairs of questions. Data were trained repeatedly with a percentage of dataset 80:20 and classified using six levels in bloom's taxonomy and based on vector embedding. The results of this study prove that the encoder-decoder model with attention produces better and easier questions than other models. Evaluation of the question-producing system by comparing the two activation functions, namely hyperbolic tangential and sigmoid, shows that the sigmoid function can reduce the value of the loss function to 0.001, which means it can minimize the error factor.

2024

Question Generation (QG) is an essential area in Natural Language Processing (NLP) that aims to create questions from a given text. This paper reviews the evolution of QG methods, from early rule-based systems to contemporary deep learning techniques, and explores potential future advancements. By examining the strengths and weaknesses of each approach, we provide a comprehensive understanding of the progress in QG and propose directions for future research.

2020 International Joint Conference on Neural Networks (IJCNN)

Automatic question generation (QG) has found applications in the education sector and to enhance human-machine interactions in chatbots. Existing neural QG models can be categorized into answer-unaware and answer-aware models. One of the main challenges faced by existing neural QG models is the degradation in performance due to the issue of one-tomany mapping, where, given a passage, both answer (query interest/question intent) and auxiliary information (context information present in the question) can result in different questions being generated. We propose a controllable question generation model (CQG) that employs an attentive sequence-to-sequence (seq2seq) based generative model with copying mechanism. The proposed CQG also incorporates query interest and auxiliary information as controllers to address the one-to-many mapping problem in QG. Two variants of embedding strategies are designed for CQG to achieve good performance. To verify its performance, an automatic labeling scheme for harvesting auxiliary information is first developed. A QG dataset is also annotated with auxiliary information from a reading comprehension dataset. Performance evaluation shows that the proposed model not only outperforms existing QG models, it also has the potential to generate multiple questions that are relevant given a single passage.

… of QG2010: The Third Workshop on …, 2010

Abstract. Question Generation (QG) and Question Answering (QA) are key challenges facing systems that interact with natural languages. The potential benefits of using automated systems to generate questions helps reduce the dependency on humans to generate ...

ArXiv, 2020

Question Generation (QG) is an important task in Natural Language Processing (NLP) that involves generating questions automatically when given a context paragraph. While many techniques exist for the task of QG, they employ complex model architectures, extensive features, and additional mechanisms to boost model performance. In this work, we show that transformer-based finetuning techniques can be used to create robust question generation systems using only a single pretrained language model, without the use of additional mechanisms, answer metadata, and extensive features. Our best model outperforms previous more complex RNN-based Seq2Seq models, with an 8.62 and a 14.27 increase in METEOR and ROUGE_L scores, respectively. We show that it also performs on par with Seq2Seq models that employ answer-awareness and other special mechanisms, despite being only a single-model system. We analyze how various factors affect the model's performance, such as input data formatting, the len...

This paper describes the question generation system devel-oped at UPenn for QGSTEC, 2010. The system uses predicate argument structures of sentences along with semantic roles for the question gener-ation task from paragraphs. The semantic role labels are used to identify relevant parts of text before forming questions over them. The generated questions are then ranked to pick final six best questions.

2020

1-4BE Computer Engineering, Sandip Institute of Technology and Research Centre, Nasik, Maharashtra, India. ---------------------------------------------------------------------***--------------------------------------------------------------------Abstract Automatic generation of questions from text plays an integral role in various domains and is a highly growing topic when one needs to apply automation. The input text is broken into tokens and questions are generated. This paper states a standard methodology for automated question generation. It focuses on the examination of both semantic and syntactic format of a sentence. Various NLP libraries such as Spacy, NLTK are used for tokenization, stemming, lemmatization, punctuation. Part of Speech tagging is one of the most significant parts of natural language processing which helps us to find the proper tag for given text. Using these NLP libraries the proposed system performs effectively utilizing paragraphs of text as input. The sy...

Question Generation is a field of research that has been growing in popularity through the years, as educators seek to find ways to make test generation a lot easier with the use of Machine Learning and Artificial Intelligence. In this paper we research how automated end-to-end question generation that utilizes transformers will generate an understandable question by making an inference on sample paragraphs. The model is trained in an end-to-end approach where the model focuses on the context paragraph to understand the sentences and generate a question where the answer is not directly in the context paragraph. An inference approach is proposed to find hidden sentences by using discourse analysis and paraphrasing techniques based on fine tuning transformers to be fed into a model that can generate a question from the hidden or new sentences. The Stanford parser was also utilized to get a clearer view of the parts of speech focusing particularly on the verbs, pronouns, and other key entities in the sentence. Experiments on the context paragraphs was conducted on the SQuAD 1.1 dataset where we attempted to transform the original input paragraphs using the inference rule. After transforming all sentences, we then fed these new shortened paragraphs to the transformer model to generate a deeper level understanding question.