NLP #DPR1 DPR: Dense Passage Retrieval for Open-Domain Question Answering DPR: Dense Passage Retrieval for Open-Domain Question Answering Code : https://github.com/facebookresearch/DPR Paper : https://arxiv.org/pdf/2004.04906.pdf Abstract Open-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 ca.. 2022. 5. 2. 이전 1 다음
