Efficient Passage Retrieval with Hashing for Open-domain Question Answering

2021-06-02 · ACL 2021 5 · 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 BibTeX arXiv:2106.00882

Code (1)

studio-ousia/bpr 공식 구현 pytorch

Tasks

Natural Questions Open-Domain Question Answering Passage Retrieval Question AnsweringRerankingRetrieval TriviaQA

Dense Passage Retrieval for Open-Domain Question Answering

2020-04-10 · EMNLP 2020 11 · Vladimir Karpukhin, Barlas Oğuz, Sewon Min, Patrick Lewis 외

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…

Open-Domain Question Answering Passage Retrieval Question Answering Retrieval

Improving Passage Retrieval with Zero-Shot Question Generation

2022-04-15 · Devendra Singh Sachan, Mike Lewis, Mandar Joshi, Armen Aghajanyan 외

We propose a simple and effective re-ranking method for improving passage retrieval in open question answering. The re-ranker re-scores retrieved passages with a zero-shot question generation model, which uses a pre-trai…

Language Modeling Language Modelling Open-Domain Question Answering Open-Ended Question Answering+6

xMoCo: Cross Momentum Contrastive Learning for Open-Domain Question Answering

2021-08-01 · ACL 2021 5 · Nan Yang, Furu Wei, Binxing Jiao, Daxing Jiang 외

Dense passage retrieval has been shown to be an effective approach for information retrieval tasks such as open domain question answering. Under this paradigm, a dual-encoder model is learned to encode questions and pass…

Contrastive Learning Information Retrieval Open-Domain Question Answering Passage Retrieval+2

Knowledge Guided Text Retrieval and Reading for Open Domain Question Answering

2019-11-10 · Sewon Min, Danqi Chen, Luke Zettlemoyer, Hannaneh Hajishirzi

We introduce an approach for open-domain question answering (QA) that retrieves and reads a passage graph, where vertices are passages of text and edges represent relationships that are derived from an external knowledge…

Natural Questions Open-Domain Question Answering Question Answering Reading Comprehension+4

Dense Hierarchical Retrieval for Open-Domain Question Answering

2021-10-28 · Findings (EMNLP) 2021 11 · Ye Liu, Kazuma Hashimoto, Yingbo Zhou, Semih Yavuz 외

Dense neural text retrieval has achieved promising results on open-domain Question Answering (QA), where latent representations of questions and passages are exploited for maximum inner product search in the retrieval pr…

Open-Domain Question Answering Question Answering Retrieval Text Retrieval