Sign inSign up

dicegroup/tebaqa

By dicegroup

•Updated over 5 years ago

A question answering system which utilises machine learning.

Image
0

332

dicegroup/tebaqa repository overview

⁠Template-Based Question Answering

Build Status Codacy Badge

⁠Preview

⁠Execution

  • Checkout the project
  • Execute the following command in the root directory to start the server: mvn spring-boot:run
⁠Docker

First install docker in your system. For ubuntu you may refer to below link. [https://www.digitalocean.com/community/tutorials/how-to-install-and-use-docker-on-ubuntu-16-04⁠]

For windows users [https://docs.docker.com/toolbox/toolbox_install_windows/#step-1-check-your-version⁠]

Move to the parent directory of project and execute the below commands

mvn clean
mvn package

Now to build your image, type the below command.

sudo docker build -f Dockerfile -t tebaqa .

To run your image, type the below command.

sudo docker run -d -p 8187:8080 -t tebaqa --restart always

It will be available under localhost:8187

⁠Citation

Vollmers, D., Jalota, R., Moussallem, D., Topiwala, H., Ngomo, A. C. N., & Usbeck, R. (2021). Knowledge Graph Question Answering using Graph-Pattern Isomorphism. arXiv preprint arXiv:2103.06752. https://arxiv.org/abs/2103.06752⁠

⁠Question Answering

  • To answer a question simply execute a HTTP POST request to
  • Parameters:
    • query: A string which contains a question (required).
    • lang: The language of the question (default:en) Note: Other languages than English haven't been implemented yet.
  • An example request could look like this:
    • http://localhost:8181/qa?query=What is the original title of the interpretation of dreams?&lang=en

⁠Evaluation

⁠Ablation study

⁠Credit

Tag summary

Content type

Image

Digest

Size

944.6 MB

Last updated

over 5 years ago

docker pull dicegroup/tebaqa