This research topic can only be taken by Thesis route and Project route student. This research topic's objectives are:
- knowledge graph extraction, in Python, from either PDF texts "Healthy Parents, Healthy Children - Pregancy and Birth" and "Healthy Parents, Healthy Children - The Early Years" (downloadable at https://www.healthyparentshealthychildren.ca/resources/printables) or BioASQ training data set for task 13b (downloadable by clicking the Training 13b under Datasets for task b at https://participants-area.bioasq.org/datasets/ after register and sign in);
- web-based interactive knowledge graph development in PHP;
- extract and summarize texts that are associated the identified subgraph according to the question entered by the user;
- performance evaluation include speed and accuracy comparisons; and,
- for thesis students only, examine outcome via well-designed experiment for quanititative and qualitative data analysis.
Tasks of this research include:
- Conducting a systematic literature review on relevant academic literature and research -- usually this step is the first step for a master research project/thesis topi; however due to the pandemaic, this one will be postponed prior task #8.
- Designing and implementing a mechanism (in Python script running on a Ubuntu 24.04 LTS or newer Ubuntu version cloud-based server) that can extract concepts and store knowledge graph in mySQL database from the 33,000 full text. All relevant functions have to be developed in modularized way with classes and memeber functions to give flexibility and reusability in future development and enhancement for working with other systems.
- Recording all the time spent that each stage in the proposed mechanism has, so the performance evaluation can be done later.
- Having proper web-based interactive user interface in PHP to get the knowledge graph.
- Designing and implementing a mechanism (in PHP running on a Ubuntu 24.04 LTS or newer Ubuntu version cloud-based operating system) that can identify the subgraph via the extraction of key words of a question.
- Having the identified subgraph's nodes and edges on the knowledge graph on the web-based interactive user interface in PHP.
- Summarizing the text associated to the subgraph and form the answer of the question -- for BioASQ dataset, the test questions are coming from the test dataset that can be downloaded by clicking 13b golden enriched under Datasets for task b at https://participants-area.bioasq.org/datasets/ after register and sign in.
- Planning, conducting and collecting data for the usability evaluation.
For taking this topic, the student is better to have the following skills or knowledge:
- Familiar with XML, JSON, HTML, CSS, Java Script, and AJAX
- Having experience in developing web-based application with PHP
- Having experience in developing application with Python
- Familiar with command mode of Debian or other Linux system.
- Information collection, re-organization, summarization, and reports.
- Using screen capture software and video editing software/tool to creating instructional video clips
|
