PrimeQA is a public open source repository that enables researchers and developers to train state-of-the-art models for question answering (QA). By using PrimeQA, a researcher can replicate the experiments outlined in a paper published in the latest NLP conference while also enjoying the capability to download pre-trained models (from an online repository) and run them on their own custom data. PrimeQA is built on top of the Transformers toolkit and uses datasets and models that are directly downloadable. Note: that we have 4 repositories under PrimeQA with the first 2 serving most of your needs. Demo paper outlining PrimeQA and its capabilities are available here.
- primeqa: The main PrimeQA repository for training custom QA models, replicating the SOTA in QA research/ academia and notebooks.
- create-primeqa-app: This repository provides easy scripts to run PrimeQA applications via docker.
- primeqa-ui: Front-end for PrimeQA services
- primeqa-orchestrator: Orchestrator connecting different PrimeQA components
The models within PrimeQA supports End-to-end Question Answering. PrimeQA answers questions via
- Information Retrieval: Retrieving documents and passages using both traditional (e.g. BM25) and neural (e.g. ColBERT) models
- Multilingual Machine Reading Comprehension: Extract and/ or generate answers given the source document or passage.
- Multilingual Question Generation: Supports generation of questions for effective domain adaptation over tables and multilingual text.
For more details, please look into the individual repositories.