Chatbot for education has great potential to complement human educators and education administrators. For example, it can be around the clock tutor to answer and clarify any questions from students who may have missed class. A chatbot can be implemented either by ruled based or artificial intel-ligence based. However, unlike the ruled-based chatbots, artificial intelli-gence based chatbots can learn and become smarter overtime and is more scalable and has become the popular choice for chatbot researchers recently. Recurrent Neural Network based Sequence-to-sequence (Seq2Seq) model is one of the most commonly researched model to implement artificial intelli-gence chatbot and has shown great progress since its introduction in 2014. However, it is still in infancy and has not been applied widely in educational chatbot development. Introduced originally for neural machine translation, the Seq2Seq model has been adapted for conversation modelling including question-answering chatbots. However, in-depth research and analysis of op-timal settings of the various components of Seq2Seq model for natural an-swer generation problem is very limited. Additionally, there has been no ex-periments and analysis conducted to understand how Seq2Seq model handles variations is questions posed to it to generate correct answers. Our experi-ments add to the empirical evaluations on Seq2Seq literature and provides insights to these questions. Additionally, we provide insights on how a cu-rated dataset can be developed and questions designed to train and test the performance of a Seq2Seq based question-answer model.

Software optical mark recognition (SOMR) is the process whereby information entered on a survey form or questionnaire is converted using specialized software into a machine-readable format. SOMR normally requires input fields to be completely darkened, have no internal labels, or be filled with a soft pencil, otherwise mark detection will be inaccurate. Forms can also have print and scan artefacts that further increase the error rate. This article presents a new method of mark detection that improves over existing techniques based on pixel counting and simple thresholding. Its main advantage is that it can be used under a variety of conditions and yet maintain a high level of accuracy that is sufficient for scientific applications. Field testing shows no software misclassification in 5695 samples filled by trained personnel, and only two misclassifications in 6000 samples filled by untrained respondents. Sensitivity, specificity, and accuracy were 99.73%, 99.98%, and 99.94% respectively, even in the presence of print and scan artefacts, which was superior to other methods tested. A separate direct comparison for mark detection showed a sensitivity, specificity, and accuracy respectively of 99.7%, 100.0%, 100.0% (new method), 96.3%, 96.0%, 96.1% (pixel counting), and 99.9%, 99.8%, 99.8% (simple thresholding) on clean forms, and 100.0%, 99.1%, 99.3% (new method), 98.4%, 95.6%, 96.2% (pixel counting), 100.0%, 38.3%, 51.4% (simple thresholding) on forms with print artefacts. This method is designed for bubble and box fields, while other types such as handwriting fields require separate error control measures.

There is a great interest shown by academic researchers to continuously improve the sequence-to-sequence (Seq2Seq) model for natural answer generation (NAG) in chatbots. The Seq2Seq model shows a weakness whereby the model tends to generate answers that are generic, meaningless and inconsistent with the questions. However, a comprehensive literature review on the factors contributing to the weakness and potential solutions are still missing. Therefore, this review article fills the gap by reviewing Seq2Seq based natural answer generation-based literature to identify those factors and proposed methods to address the weakness. This literature review identified several factors such as input question is not sufficient to determine a meaningful output, usage of cross-entropy function as the loss function during training, infrequent words in training data, language model influence which generates answers not relevant to the question, utilization of teacher forcing method during training which results in exposure bias, long sentences and inability to consider dialogue history as the factors. Additionally, this literature review also identified and reviewed the methods proposed to address the weakness such as utilizing additional embedding and encoders, using different loss functions and training approaches, as well as utilizing other mechanisms like copying source word(s) and paying attention to a certain portion of the input. For discussion, these methods are categorized into four broad categories which are Structural Modifications, Augmented Learning, Beam Search and Complementary Mechanisms. Additionally, the paper highlights unexplored areas in Seq2Seq modeling and proposes potential future works for natural answer generation. INDEX TERMS Seq2Seq, natural answer generation, natural language processing, dialogue generation, chatbot.

No abstract

No abstract