4 minute read
A.I. Assisted Pedagogical Chatbot
AI-assisted pedagogical chatbot
ANDREW EMANUEL ATTARD | SUPERVISOR:Prof. Alexiei Dingli COURSE: B.Sc. IT (Hons.) Artificial Intelligence
Advertisement
The traditional classroom setting features a single educator, who is tasked with educating multiple students. This paradigm is fundamentally flawed, when , considering that the number of students requiring constant attention and educational monitoring throughout their studies is quite high, when compared with the number of available educators equipped to assist them.
Taking the above premise as point of departure, this study focused specifically on the teaching of mathematics, which is especially challenging in this regard. This is primarily due to the nature of mathematics, which require the assimilation of a concept in order to grasp the next topic. Therefore, if a student were to fall short of understanding one concept, this would negatively affect the student’s ability to solve problems relating to the ensuing topic.
This project aims to help solve this issue by enabling educators to automatically generate chatbots that their students can use. The chatbot was created by obtaining basic maths lessons from the educator and then generating a chatbot that is capable of providing the required explanation when asked. Chatbot systems generally work by detecting what the user wants to, based on their input (often referred to as ‘user intent’ in modern systems) and then outputting the correct response. Since chatbots require a template of what the user might say in a conversation, possible questions were extracted from the explanations provided, through a dedicated question extraction component. Meanwhile, the list of outputs that the chatbot offered in response to the user’s request was populated by not only the given explanations but also by explanations that would have been generated by the system.
The explanations generated by the system were produced through a dedicated subcomponent capable of fine-tuning a generative model to create explanations that would be close to the explanations originally provided by the educator. Despite generative models generally creating high-quality text when properly trained and duly fine-tuned, there was an element of unpredictability, where the output might not necessarily be of suitable quality. Hence, a multinomial naive Bayes classifier was developed to filter out any low-quality explanations that would have been produced by the generative model. Once the explanations were generated, a numerical substitution system was deployed to generate a variety of explanations with different numbers, while successfully maintaining the relationship between the numbers in a given explanation.
Once the possible questions and the explanations were generated, the data was then written into a chatbot domain file. It was then used to train, and subsequently deploy, a chatbot that could be used by the student. This resulted in a chatbot that would provide the student with the required explanation, worded in a style similar to that of the student’s educator.
Figure 1. Example of student-chatbot interaction
Grammar and spell-checking techniques for Maltese
MATTHIAS BUHAGIAR | SUPERVISOR: Dr Colin Layfield | CO-SUPERVISOR: Prof. John M. Abela COURSE: B.Sc. IT (Hons.) Computing and Business
This project discusses and applies grammar and spellchecking techniques to Maltese. Although spell-checkers are also available for this language, the suggestions they offer do not always meet user expectations. Additionally, no grammar checker for Maltese has been developed to date.
Using a novel Soundex approach, the spell-checker developed promises to offer many more accurate suggestions. This is because it utilises the pronunciation of words, as well as the character distance between words. Therefore, while other spell-checking techniques find it difficult to suggest ‘għamluhomlhom’ for ‘amluhomlom’, this would be possible if using the Soundex. Moreover, correct words with a pronunciation similar to a misspelling could obtain a higher ranking. Thus, ‘ċerv’ and ‘ħabib’ would receive a higher ranking for the misspellings ‘ċerf’ and ‘ħabip’.
Apart from using the pronunciation of words to obtain suggestions, the Symmetric Delete algorithm was used to obtain words within a certain character edit distance. This means that ‘rabatli’ is capable of being generated for ‘ravatli’, or ‘kellimni’ for ‘kellinmi’.
The rule-based grammar checker uses an XML rule base that is easily extendible. Only minimal knowledge of the inner workings of the system would be necessary to expand the rules. Some of the rules developed include: checking for the correct use of the ‘-il’ particle that should be tagged onto the numbers eleven to nineteen when immediately followed by nouns (e.g., ‘tnax-il ktieb’) and checking that the definite article would correspond to the noun (e.g., correcting ‘il-xemx’ to ‘ix-xemx’)
A web-based user interface was provided to enable the user to write text and receive corrections. Words were marked in red to indicate an orthographic error and in blue to indicate a grammatical error. Suggested corrections could then be applied by selecting them.
Figure 1. Overview of the system
Figure 2. Web interface of the grammar and spellchecker