BPR
Binary Passage Retriever (BPR) is an efficient neural retrieval model for open-domain question answering. BPR integrates a learning-to-hash technique into Dense Passage Retriever (DPR) to represent the passage embeddings using compact binary codes rather than continuous vectors. It substantially reduces the memory size without a loss of accuracy tested on Natural Questions and TriviaQA datasets.
BPR was originally developed to improve the computational efficiency of the SÅseki question answering system submitted to the Systems under 6GB track in the NeurIPS 2020 EfficientQA competition. Please refer to our ACL 2021 paper for further technical details.
Installation
BPR can be installed using Poetry:
poetry install
The virtual environment automatically created by Poetry can be activated by poetry shell.
Alternatively, you can install required libraries using pip:
pip install -r requirements.txt
Trained Models
(coming soon)
Reproducing Experiments
Before you start, you need to download the datasets available on the DPR website into <DPR_DATASET_DIR>.
The experimental results on the Natural Questions dataset can be reproduced by running the commands provided in this section. We used a server with 8 NVIDIA Tesla V100 GPUs with 16GB memory in the experiments. The results on the TriviaQA dataset can be reproduced by changing the file names of the input dataset to the corresponding ones (e.g., nq-train.json -> trivia-train.json).
1. Building passage database
python build_passage_db.py \
--passage_file=<DPR_DATASET_DIR>/wikipedia_split/psgs_w100.tsv \
--output_file=<PASSAGE_DB_FILE>
2. Training BPR
python train_biencoder.py \
--gpus=8 \
--distributed_backend=ddp \
--train_file=<DPR_DATASET_DIR>/retriever/nq-train.json \
--eval_file=<DPR_DATASET_DIR>/retriever/nq-dev.json \
--gradient_clip_val=2.0 \
--max_epochs=40 \
--binary
3. Building passage embeddings
python generate_embeddings.py \
--biencoder_file=<BPR_CHECKPOINT_FILE> \
--output_file=<EMBEDDING_FILE> \
--passage_db_file=<PASSAGE_DB_FILE> \
--batch_size=4096 \
--parallel
4. Evaluating BPR
python evaluate_retriever.py \
--binary_k=1000 \
--biencoder_file=<BPR_CHECKPOINT_FILE> \
--embedding_file=<EMBEDDING_FILE> \
--passage_db_file=<PASSAGE_DB_FILE> \
--qa_file=<DPR_DATASET_DIR>/retriever/qas/nq-test.csv \
--parallel
5. Creating dataset for reader
python evaluate_retriever.py \
--binary_k=1000 \
--biencoder_file=<BPR_CHECKPOINT_FILE> \
--embedding_file=<EMBEDDING_FILE> \
--passage_db_file=<PASSAGE_DB_FILE> \
--qa_file=<DPR_DATASET_DIR>/retriever/qas/nq-train.csv \
--output_file=<READER_TRAIN_FILE> \
--top_k=200 \
--parallel
python evaluate_retriever.py \
--binary_k=1000 \
--biencoder_file=<BPR_CHECKPOINT_FILE> \
--embedding_file=<EMBEDDING_FILE> \
--passage_db_file=<PASSAGE_DB_FILE> \
--qa_file=<DPR_DATASET_DIR>/retriever/qas/nq-dev.csv \
--output_file=<READER_DEV_FILE> \
--top_k=200 \
--parallel
python evaluate_retriever.py \
--binary_k=1000 \
--biencoder_file=<BPR_CHECKPOINT_FILE> \
--embedding_file=<EMBEDDING_FILE> \
--passage_db_file=<PASSAGE_DB_FILE> \
--qa_file==<DPR_DATASET_DIR>/retriever/qas/nq-test.csv \
--output_file=<READER_TEST_FILE> \
--top_k=200 \
--parallel
6. Training reader
python train_reader.py \
--gpus=8 \
--distributed_backend=ddp \
--train_file=<READER_TRAIN_FILE> \
--validation_file=<READER_DEV_FILE> \
--test_file=<READER_TEST_FILE> \
--learning_rate=2e-5 \
--max_epochs=20 \
--accumulate_grad_batches=4 \
--nq_gold_train_file=<DPR_DATASET_DIR>/gold_passages_info/nq_train.json \
--nq_gold_validation_file=<DPR_DATASET_DIR>/gold_passages_info/nq_dev.json \
--nq_gold_test_file=<DPR_DATASET_DIR>/gold_passages_info/nq_test.json \
--train_batch_size=1 \
--eval_batch_size=2 \
--gradient_clip_val=2.0
7. Evaluating reader
python evaluate_reader.py \
--gpus=8 \
--distributed_backend=ddp \
--checkpoint_file=<READER_CHECKPOINT_FILE> \
--eval_batch_size=1
License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Citation
If you find this work useful, please cite the following paper:
@inproceedings{yamada2021bpr,
title={Efficient Passage Retrieval with Hashing for Open-domain Question Answering},
author={Ikuya Yamada and Akari Asai and Hannaneh Hajishirzi},
booktitle={ACL},
year={2021}
}
20 Nov 25, 2022
52 Nov 21, 2022
1 Nov 08, 2022
3 May 01, 2022
1 Jan 23, 2022
99 Dec 27, 2022
112 Dec 27, 2022
8 Apr 03, 2022
66 Nov 08, 2022
188 Jan 06, 2023
2 Aug 20, 2022
11 Sep 28, 2022
7 Dec 01, 2022
164 Oct 30, 2022
8 Sep 06, 2021
15 Jul 06, 2022
146 Dec 18, 2022
135 Dec 14, 2022
21 Nov 24, 2022
85 Jan 04, 2023