Ask4Summary: Summary Generation Service for User’s Questions


The service aims to use the VIP Research Group's N-Gram and POS Service and the Ask4Summary algorithm to scan course content and provide users a summary for their question. The research goal is to have the automatic answering service correctly identifying the keys from a question and summarizing the associated content that is relevant to the question and makes the user satisfied.
This project is under supervision of Dr. Maiga Chang, Professor at the School of Computing and Information Systems, Athabasca University.

About the Project

While the generative AI is popular with the public, the dataset used for training the generative AI is too broad to be helpful for teaching and learning. For example, a teacher believes concept #A is more important than concept #B and has supplied all course materials and supplemental readings to students reflective of this concept weighting. If their students then use a generative AI tool trained with different dataset, which emphasizes concept #B, students might learn different materials and could even fail subsequent course exams.
Ask4Summary has a system periodically running backend services to process course's learning materials and answers user questions by identifying relevant content and generating summaries only based on the provided materials.
Ask4Summary has reached 82.69% success rate for providing quick (0.766 seconds in average) responses of course relevant questions and is available for users in interactive web, Moodle plug-in form, and Python library.Ask4Summary is a Moodle plugin aiming to provide users with a summary based on part of speech similarity to their question.
Ask4Summary plugin will go through course material, gather the sentences - and their N-Grams and Part of Speech - and store it into its learning database. Afterwards, when a user asks a question, it will compare the N-Grams taken from their sentences and produce a similarity coefficient from the frequency of those same N-Grams in the learning database. Then, it will return the most comparable sentences.

  • Ask4Summary service will identify the keyphrases from a question entered by a user with Natural Language Processing techniques.
  • The course material scanned remains in the database, allowing fast lookup in Ask4Summary's learning tables.
  • Ask4Summary plugin can return up to 12 comparable sentences for any user question, from up to 5 documents in the course.
  • The plugin currently supports use of Word Documents, Powerpoint Presentations, PDFs, URL webpages, and built in Moodle Pages.

Services

N-Gram POS Service

Ask4Summary uses the VIP Research Group's N-Gram POS Service - it collects N-Grams validated by the top 15 parts of speech from the DBPedia database.

AskCOVIDQ

Ask4Summary derives the summary algorithm from the VIP Research Group's ASKCOVIDQ serivce. It utilizies cosine similarity on vectors created from the frequency of N-Grams in the user's question, and the learning database.

How to Access

Downloads

...
Plugin Directory

Access the Moodle plugin directory for Ask4Summary.

...
Github Repository

Access the repository for Ask4Summary directly.

About Us

...
Our Mission

Our research aims to utilize the VIP Research Group's services to make all users benefit from our research outcome.

...
Our Supervisor

Dr. Maiga Chang is a Full Professor in the School of Computing and Information Systems at Athabasca University, Canada.

...
Research Goal

The research goal is to have the automatic answering service correctly identifying the keys from a question and summarizing the associated content that is relevant to the question and makes the user satisfied.

Our Team

Team Member
Yian Chu
2025

Yian is an undergraduate student at Chung Yuan Christian University, pursuing a bachelor's degree in Information and Computer Engineering.

Team Member
Shayaan Malik
2025

Shayaan Malik joined the team in June 2025. He graduated from the National University of Science and Technology, Pakistan, and is currently working on the Ask4Summary project.

...
Maria IRIARTE
2022~2023

Maria is a Charter Civil Engineer specialized in data science and spatial analysis for large public and environmental infrastructures, holding a Master's Degree in Big Data & Visual Analytics and in Occupational Risk Prevention. Maria is currently writing her PhD doctoral thesis in Computer Science at the International University of La Rioja and pursuing a Master of Science in Information Systems at Athabasca University.

...
Supun DE SILVA
2022

Supun De Silva is an undergraduate student at Athabasca University pursuing a Bachelor of Science majoring in Computing Information Systems with a minor in Game Programming. My current research interest is in artificial intelligence in education, specifically identifying student learning weaknesses and providing adaptive feedback. Other areas of interest include cloud computing, system administration, web-based system development, network programming, database administration, game programming, and system analysis and design. Outside of schoolwork, I like reading books and weightlifting.

...
Mohammed SALEH
2022

Mohammed Saleh is an undergraduate student at the University of Alberta, pursuing a Bachelor's degree in Computer Software Engineering. His main research focus was the development of the Ask4Summary plugin; but, Mohammed is also interested in software development and video game production. Other than computing, Mohammed enjoys the outdoors and sports.

...
Mikhail VINOGRADOV
2021

Mikhail Vinogradov is a Software Developer and Cloud Practitioner with a passion for innovation and solving problems through technology. His extracurricular interests include Machine Learning, Artificial Intelligence, Systems Architecture, and Biotechnology. He recently completed his Master's of Information Systems at Athabasca University and is looking for his next project to pursue his PhD.

...
Sayantan PAL
2021

Sayantan Pal was an undergraduate student pursuing Computer Science and Engineering from Heritage Institute of Technology, India. His research interest lies in the domain of Machine Learning and Natural Language Processing. In 2022 he had been accepted by the Doctorate of Philosophy in Computer Science & Engineering program at the University at Buffalo, The State University of New York with full-time Teaching Assistant appointment and Chair's Fellowship.

Videos


Installation

The installation process of Ask4Summary.

  1. Installation from the Plugin Directory
  2. Installation directly into Moodle files


Configuration

The administrator and teacher configuration of Ask4Summary.

  1. 0:00 to 2:35 - Administrator specific settings
  2. 2:35 to end - Block configuration settings


Teacher Use

A guide on how teachers can use Ask4Summary.

  1. How to use the Logistics page
  2. How to optimize course resource scanning


Student Use

A guide on how students can use Ask4Summary.

  1. How to ask a question
  2. How to view the response


Presentation Video

Live demonstrations on a 12-weeks work outcome (May 2021~July 2021) of the preliminary function of Coronavirus Question Answering research in Python, PHP, JavaScript (AJAX and JSON), and Natural Language Processing basics. It includes three stages:

  1. Stage 1: File Extraction and Verification
  2. Stage 2: Data Processing
  3. Stage 3: Summary Generation


Stage 1: File Extraction and Verification

Stage 1's major features include (but not limited to)

  1. File extraction and verification on uploaded CORD-19 dataset in compressed tar and/or gz file format.
  2. Cron jobs for the backend services.
  3. Dashboard that shows backend services' working progress.


Stage 2: Data Processing

Stage 2's major features include (but not limited to)

  1. Processing CORD-19 dataset's fulltext in JSON format.
  2. Analyzing and summarizing useful Part-of-Speech (PoS) tags in CORD-19 dataset.
  3. Storing useful PoS tags and relevant n-grams (n is from 1 to 4).


Stage 3: Summary Generation

Stage 3's major features include (but not limited to)

  1. Web-based user interface for users to ask their questions related to coronavirus.
  2. Consine similarity calculation based on the extracted useful PoS tags and their correspondent n-grams from the asked question.
  3. Summary generation and storing for the asked questions.

Frequently Asked Questions

  • The research goal is to have an automatic answering service that correctly identifies the keys from a question. It summarizes the associated content that is relevant to the question and makes the user satisfied.

  • Ask4Summary can be used as a question and answer service for your Moodle course. It will attempt to get sentence content from your course material, and return an answer to the user.

  • We are strictly against the idea of collecting user-sensitive data. We store an anonymous system-generated user UUID as a cookie that identifies the user. We keep the question and the summary generated in our database and store them in cookies for a better experience.

  • No, we are against storing user's personal information. No questions will be shared or publicly available. We keep the question and the summary in our database for a better user experience. We uniquely identify you by a system-generated UUID and store it in a cookie.

  • Ask4Summary uses two of the VIP Research Group's services - the N-Gram POS service, and the Ask4Summary summary algorithm. Ask4Summary directly uses the N-Gram POS service to get the N-Grams and Part of Speech from the user's question and the course material. Then, it uses a derivation of the Ask4Summary summary algorithm to produce a response based on frequency of N-Grams in the question and in the database.

  • You can ask anything related to the subject you selected. This service aims to generate a summary based on the question asked.

  • We are processing the documents by extracting the sentences, followed by the extraction of n-grams and their part-of-speech tags (e.g., verb, noun, etc.) in a sentence. When the user asks a question, we identify the keywords (n-grams) from the question and create a vector representation. A vector consists of the frequency of the keywords. The vector is taken to compare with all the vectors that represent documents with Cosine similarity method. This way, we identify the best document. Similarly, we match the question vector again to the vectors that represent all sentences of the selected documents (i.e., top N documents, by default, N value is 2 here) by cosine similarity to find the best matching sentences (i.e., top M sentences, by default, M value is 5 here). We then concatenate the top M sentences to generate the summary.

  • Ask4Summary has reached 82.69% success rate for providing quick (0.766 seconds in average) responses of course relevant questions. See

    Rita Kuo, Maria F. Iriarte, Di Zou and Maiga Chang. (2023). Preliminary Performance Assessment on Ask4Summary’s Reading Methods for Summary Generation. In: 19th International Conference on Intelligent Tutoring Systems, (ITS 2023), Hybrid, Corfu, Greece, June 2-June 5, 2023, 630-637. (Springer)

  • Check the Installation, Configuration and Teacher Use videos above for a comprehensive guide on Ask4Summary.

  • Yes, Ask4Summary may be updated in the future to improve the course material scanning, the N-Gram POS service, and the summary algorithm in the future; but, there is no immediate plan to do so.