Open QA
task
ID: openqa
Related Papers
Dense Passage Retrieval for Open-Domain Question Answering
AbstractOpen-domain question answering relies on efficient passage retrieval to select candidate contexts, where traditional sparse vector space models, such as TF-IDF or BM25, are the de facto method. In this …...
Reduce Catastrophic Forgetting of Dense Retrieval Training with Teleportation Negatives
AbstractIn this paper, we investigate the instability in the standard dense retrieval training, which iterates between model training and hard negative selection using the being-trained model. We show the catastrophic …...
Questions Are All You Need to Train a Dense Passage Retriever
AbstractWe introduce ART, a new corpus-level autoencoding approach for training dense retrieval models that does not require any labeled training data. Dense retrieval is a central challenge for open-domain tasks, …...