DBpedia eXplainable Chatbot (DBpedia XChat) - GSoC 2023

DBpedia has done a great job of collecting and organizing data. Data accessibility is the key to a better understanding of the world and a foundation of Data Literacy, a crucial competence for the current generation. In 2021, a DBpedia GSoC project [1] led to the development of a Dialogflow-based chatbot that enables users to access the DBpedia Knowledge Graph (KG) using Natural Language (NL). The chatbot provides Question Answering (QA) functionality, i.e., searching for facts that are answering NL questions. During the GSoC 2023, we will continue the DBpedia Chatbot initiative.

The core idea of the DBpedia eXplainable Chatbot – short: DBpedia XChat – is to be configurable on-the-fly. Users can choose components that process a question (i.e., SpaCy, Falcon), change working language, and also get explanations regarding the intermediate processing steps and components’ behavior.

The current architecture of the DBpedia Chatbot consists of three layers:

  • Google Dialogflow frontend — generates the UI and handles the intent recognition logic (developed using Google’s platform)
  • DBpedia Chatbot backend — handles requests from the frontend regarding the general intents: “hello!”, “what can you do?”, and custom features: change language, choose QA components, etc. (developed with JavaScript and Python)
  • Qanary QA framework [2] — orchestrates the QA components and does the QA process if a question is fact-oriented, e.g., “Who is the CEO of Google?” (developed with Java and Python).

The activity diagram below demonstrates the interaction of the architectural layers of the Chatbot.

Figure — Activity Diagram of the DBpedia Chatbot’s architectural layers

This year, we are going to tackle the unsolved challenge of the DBpedia Chatbot and hence, define the following goals:

  1. Work with the current codebase.
  • Refine and prettify the current codebase (s.t., the code becomes readable and supportable)
  • Setting CI/CD for the solution using a public server (will be given by project supervisors)
  1. Introduce new features to the chatbot.
  • Provide a user with better access to internal information, s.t., the Question Answering process becomes a “glass box” instead of a “black box”. For this purpose, new dialog scenarios need to be created with additional visualizations or rich responses.
  • Implement a dialog scenario to get an overview of the Qanary QA pipeline configuration and of its components.
  • Implement a scenario, where for each Qanary Component, a user should be able to see detailed information and description.
  • Optionally, a visualization of the QA pipeline (ASCII-art or better) would benefit users.
  1. Evaluation of the DBpedia chatbot.
  • Validate the answers by measuring the Question Answering quality.
  • Run A/B tests with real users to understand how explainability influences users’ satisfaction.
  1. As the overall goal is to improve the answer quality, additional Machine Learning components might be used to create recommendations for improved QA pipeline configurations (e.g., if a component has a low confidence score, then another one should be suggested).
  • In detail, this means that you might run different pipeline configurations while training to then start the best-suited pipeline on test time. Here, a simple, hugging face-based LLM fine-tuned on a large dataset such as LC-QuAD 2 or GRAIL-QA could be used.

The impact of this work would be:

  • Refinement, stabilizing, and setting CI/CD for the current codebase.
  • Integration of explainability/traceability of search results (“glass box” behavior to help users to understand the search behavior).
  • Identification of typical misbehavior of the chatbot and creation of requests for improvements of processing steps that might fail often.
  • Scientific study on the impact of the explainability feature on users’ satisfaction with the system.

Warm-up tasks:

Requirements for applicants:

  • Good knowledge of Software Engineering
  • Fluency with Python and JavaScript
  • Good understanding of RESTful APIs and ability to implement one
  • Experience with Natural Language Processing (e.g., University Projects)
  • Understanding of Resource Description Framework and SPARQL
  • Basic knowledge of Shell scripting (e.g., ssh connection to a server)
  • Basic understanding of CI/CD: Docker, GitHub Actions

The project size can follow the medium (~175 hours) or large (~350 hours) format. However, we prefer the large format as it provides more opportunities to increase the impact.


Please, express your interest here at the forum or use the Github accounts listed above. Also, feel free to join the DBpedia Slack workspace by visiting Slack and write us there.

Scientific Contribution: We are open to working together with the project participant on preparing a scientific publication based on the project results targeting top-tier conferences (WWW, ESWC, ACL, etc.).

Keywords: Question Answering, Natural Language Processing, Natural language Understanding, Named Entity Recognition, Machine Learning, Explainable AI, Knowledge Graphs, Linked Data, Semantic Web, Python, JavaScript.


[1] GSoC 2021 project: Modular DBpedia Chatbot

[2] GitHub - WDAqua/Qanary: Qanary a methodology to construct and share resources to build QA systems

[3] Home · WDAqua/Qanary Wiki · GitHub

Hello @perevalov My name is Abdulsobur Oyewale. From the description of this project, fine-tuning a model to fit the project’s needs is allowed, right?

Also, considering the user base, will the results of this project be restricted to English speakers only, or will other popular languages also be considered when fine-tuning the models?

Hi @smilingprogrammer, fine-tuning a model is indeed an important part of the project. I’d say it’s a necessity but not a sufficiency to complete the project.

We aim at multilinguality in our project, so, it’s not restricted to English.

Thanks for the clarification @perevalov

Hi! I’m Muskan Kothari, a CSE senior at PES University, India. DBpedia caught my attention among the organizations, specifically this project.

I have been working on multiple projects in NLP, machine learning and big data to accumulate basic to proficient skills, which matches this project and my interests! I am proficient in Python, Javascript, have worked with REST APIs and have numerous projects in NLP (listed below). I have basic knowledge in Shell scripting and Docker. SPARQL and Github Actions are new and I am excited to work and learn along the way!

My previous projects and associated publications include:
Lexical Diversity and Alzheimer’s detection using speech transcripts (SpaCy, pylangacq, Sklearn, Pandas, Python) - Published at 15th ICAART 2023
Sentiment Analysis on Twitter data (PySpark, Sklearn, Python)
Critical Temperature prediction of superconductors - published at INCET 2022

This project is of my interest and I look forward to working on the proposal soon. I will be spending the next couple of days going over the warm up tasks (UPDATES BELOW), although the dbpedia-chatbot-backend and Question_Answering repositories throw a 404 error.

Apart from the warm up tasks, do you recommend any other resources or tasks that could help me draft a concise and better proposal according to DBpedia and project needs? Could you also tell me by when you would prefer to have a look at the first draft?

Update: I’m onto some of the warm up tasks and have questions building up. Could we schedule a meeting? The task to run previous year’s code: there’s no precise documentation on the steps to run the code?

Looking forward to contributing!


Hi @muskan-k, thanks for observing the problems with the repository access, now they are public:

Regarding all the technical questions and meetings: would be nice if you can join DBpedia Slack and write us there (link in the post).

Regarding the first draft, I’d say that the earlier you do it, the better it would be. Feel free to send it any time to us. Make sure to check the schedule: Google Summer of Code 2023 Timeline  |  Google Developers

Please, recognize some examples of good proposals (taken from the other DBpedia project):

When reading a proposal, I personally pay attention to its readability (appropriate font, formatting, etc.). There are plenty of academic writing guides, make sure to check them. It is also important to include high-quality visualizations e.g., flowcharts, and schemas,… created by yourself.

Hello, thanks for the update. I’ve joined the Slack and posted a message on the gsoc channel. Thanks!

Greetings to all!

My name is Joel Pardo, I am a versatile professional with expertise in data science, artificial intelligence research, and entrepreneurship. I earned my data science degree from the University of Valencia, Spain and am now in the process of obtaining a master’s degree in artificial intelligence from the Polytechnical University of Madrid. Currently, I am doing an scholarship in the Ontology Engineering Group. I continue to refine my expertise and actively participate in innovative projects.

My diverse background has allowed me to develop a unique skill set that I apply to a variety of innovative projects. Proficient in programming languages such as Python, R, and SQL, mainly. I have developed my skills in various projects, leveraging tools and frameworks like TensorFlow and PyTorch between others.

One of my notable accomplishments includes developing a modular chatbot designed to aid in diagnosing vision system issues. This AI-based tool simplifies the diagnostic process, built using Python and TensorFlow, improving patient care and outcomes.

I really interested in this project. I believe my experience and passion for AI-driven solutions make me an ideal candidate to contribute to the DBpedia eXplainable Chatbot project.


Joel Pardo.

Hi Joel. Good that you have an interest in the project! Feel free to prepare and submit your proposal. If you have more detailed questions, don’t hesitate and join DBpedia’s Slack or contact us via e-mail.

1 Like