Efficient Passage Retrieval with Hashing for Open-domain Question Answering

ACL 2021  ·  Ikuya Yamada, Akari Asai, Hannaneh Hajishirzi ·

Most state-of-the-art open-domain question answering systems use a neural retrieval model to encode passages into continuous vectors and extract them from a knowledge source. However, such retrieval models often require large memory to run because of the massive size of their passage index. In this paper, we introduce Binary Passage Retriever (BPR), a memory-efficient neural retrieval model that integrates a learning-to-hash technique into the state-of-the-art Dense Passage Retriever (DPR) to represent the passage index using compact binary codes rather than continuous vectors. BPR is trained with a multi-task objective over two tasks: efficient candidate generation based on binary codes and accurate reranking based on continuous vectors. Compared with DPR, BPR substantially reduces the memory cost from 65GB to 2GB without a loss of accuracy on two standard open-domain question answering benchmarks: Natural Questions and TriviaQA. Our code and trained models are available at https://github.com/studio-ousia/bpr.

PDF Abstract ACL 2021 PDF ACL 2021 Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Open-Domain Question Answering Natural Questions BPR (linear scan; l=1000) Exact Match 41.6 # 4
Open-Domain Question Answering TQA BPR (linear scan; l=1000) Exact Match 56.8 # 2


No methods listed for this paper. Add relevant methods here