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 work, we show that retrieval can be practically implemented using dense representations alone, where embeddings are learned from a small number of questions and passages by a simple dual-enc

[yudukikun5120]

“Dense Passage Retrieval”