Skip to content

Latest commit

 

History

History
93 lines (59 loc) · 2.8 KB

README.md

File metadata and controls

93 lines (59 loc) · 2.8 KB

Q²Forge

This project provides an end-to-end pipeline to generate a dataset of (question, SPARQL query) pairs for a given Knowledge Graph (KG). The backend (Gen²KGBot) can be found at this repo.

Features

It provides the following feature:

The following diagram shows the pipeline and how Q²Forge integrates with other systems

Q²Forge pipeline

Demo video ⏯️

Teaser

Q²Forge teaser video

Full tutorial

Q²Forge full video

Conference Presentation (K-CAP 2025)

Q²Forge K-CAP Presentation

Run locally

To run locally you need to:

  1. Install the dependencies: run the command:
npm run i
  1. Start a local development server: run the command:
ng serve
  1. Visualise the result: once the server is running, open your browser and navigate to http://localhost:4200/.

Build & Deploy

To build the project run the command:

npm run dc

This will run the following command:

ng build --base-href=/q2forge/ --deploy-url=/q2forge/ --configuration=production

which will compile the project and store the build artifacts in the dist/q2forge directory.

License

See the LICENSE file.

Cite this work

Yousouf Taghzouti, Franck Michel, Tao Jiang, Louis Felix Nothias, and Fabien Gandon. 2025. Q²Forge: Minting Competency Questions and SPARQL Queries for Question-Answering Over Knowledge Graphs. In Proceedings of the 13th Knowledge Capture Conference 2025 (K-CAP '25). Association for Computing Machinery, New York, NY, USA, 74–81. https://doi.org/10.1145/3731443.3771350

See BibTex @inproceedings{10.1145/3731443.3771350, author = {Taghzouti, Yousouf and Michel, Franck and Jiang, Tao and Nothias, Louis Felix and Gandon, Fabien}, title = {Q²Forge: Minting Competency Questions and SPARQL Queries for Question-Answering Over Knowledge Graphs}, year = {2025}, isbn = {9798400718670}, publisher = {Association for Computing Machinery}, address = {New York, NY, USA}, url = {https://doi.org/10.1145/3731443.3771350}, doi = {10.1145/3731443.3771350}, booktitle = {Proceedings of the 13th Knowledge Capture Conference 2025}, pages = {74–81}, numpages = {8}, series = {K-CAP '25} }