The aim of this project is to implement a software in the form of an open API that will automatically perform a facts validation process. In Natural Language Processing (NLP) that task is called Natural language inference (NLI), where a claim is compared with a reference to determine whether it is correct. incorrect, or unrelated. The solution should be not only precise, but also be as fast as possible in order to meet production requirements. The output of this project will be a first prototype of an Automatic Fact Checking API, running on one cloud VPS instance.
Description
Description
Event Timeline
Comment Actions
Updates
- Onboarding @Trokhymovych
- We have created an instance to host the api: fact-checking.research-collaborations-api.eqiad1.wikimedia.cloud
Comment Actions
Updates
- Deployed initial version of WikiCheck API.
- Implemented NLI model endpoint
- Implemented fact checking endpoint
- Experimented with aggregation strategies
Comment Actions
Updates:
- Finished documentation for API.
- Included brief System architecture observation
- Included Pointers to the code
- Included Explanation: how to replicate the API
- Included Description of the 3 end points, and examples
Comment Actions
Updates:
- Experimented with multilingual models
- Developed a methodology to train large multilingual models that does not fit into memory
- Explored existing multilingual NLI datasets
Comment Actions
Updates
- The API has been implemented: https://nli.wmflabs.org
- Our paper was accepted on CIKM'21: https://arxiv.org/pdf/2109.00835.pdf