Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering

Last update: Dec 07, 2022

Related tags

Overview

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 Sōseki 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}
}

Binary Passage Retriever (BPR) - an efficient passage retriever for open-domain question answering

Related tags

Overview

BPR

Installation

Trained Models

Reproducing Experiments

License

Citation

Owner

Studio Ousia

Have you ever wondered how cool it would be to have your own A.I

An SE(3)-invariant autoencoder for generating the periodic structure of materials

Toward Multimodal Image-to-Image Translation

git《Tangent Space Backpropogation for 3D Transformation Groups》(CVPR 2021) GitHub:1]

Code for A Volumetric Transformer for Accurate 3D Tumor Segmentation

Finding an Unsupervised Image Segmenter in each of your Deep Generative Models

Source code for From Stars to Subgraphs

NeWT: Natural World Tasks

CMUA-Watermark: A Cross-Model Universal Adversarial Watermark for Combating Deepfakes (AAAI2022)

ManimML is a project focused on providing animations and visualizations of common machine learning concepts with the Manim Community Library.

"Learning and Analyzing Generation Order for Undirected Sequence Models" in Findings of EMNLP, 2021

Repository to run object detection on a model trained on an autonomous driving dataset.

A short and easy PyTorch implementation of E(n) Equivariant Graph Neural Networks

Audio Domain Adaptation for Acoustic Scene Classification using Disentanglement Learning

Madanalysis5 - A package for event file analysis and recasting of LHC results

TorchDistiller - a collection of the open source pytorch code for knowledge distillation, especially for the perception tasks, including semantic segmentation, depth estimation, object detection and instance segmentation.

An open source bike computer based on Raspberry Pi Zero (W, WH) with GPS and ANT+. Including offline map and navigation.

List of content farm sites like g.penzai.com.

Implementation of ResMLP, an all MLP solution to image classification, in Pytorch

Setup freqtrade/freqUI on Heroku