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

Related tags

Deep Learningbpr
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

Creative Commons 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}
}
Owner
Studio Ousia
Studio Ousia
GitHub Repository
Understanding the Effects of Datasets Characteristics on Offline Reinforcement Learning

Understanding the Effects of Datasets Characteristics on Offline Reinforcement Learning Kajetan Schweighofer1, Markus Hofmarcher1, Marius-Constantin D

Institute for Machine Learning, Johannes Kepler University Linz 17 Dec 28, 2022
The repo of the preprinting paper "Labels Are Not Perfect: Inferring Spatial Uncertainty in Object Detection"

Inferring Spatial Uncertainty in Object Detection A teaser version of the code for the paper Labels Are Not Perfect: Inferring Spatial Uncertainty in

ZINING WANG 21 Mar 03, 2022
Unity Propagation in Bayesian Networks Handling Inconsistency via Unity Smoothing

This repository contains the scripts needed to generate the results from the paper Unity Propagation in Bayesian Networks Handling Inconsistency via U

0 Jan 19, 2022
Revisting Open World Object Detection

Revisting Open World Object Detection Installation See INSTALL.md. Dataset Our new data division is based on COCO2017. We divide the training set into

58 Dec 23, 2022
Monk is a low code Deep Learning tool and a unified wrapper for Computer Vision.

Monk - A computer vision toolkit for everyone Why use Monk Issue: Want to begin learning computer vision Solution: Start with Monk's hands-on study ro

Tessellate Imaging 507 Dec 04, 2022
Feedback is important: response-aware feedback mechanism for background based conversation

RFM The code for the paper: "Feedback is important: response-aware feedback mechanism for background based conversation." Requirements python 3.7 pyto

Jiatao Chen 2 Sep 29, 2022
DivNoising is an unsupervised denoising method to generate diverse denoised samples for any noisy input image. This repository contains the code to reproduce the results reported in the paper https://openreview.net/pdf?id=agHLCOBM5jP

DivNoising: Diversity Denoising with Fully Convolutional Variational Autoencoders Mangal Prakash1, Alexander Krull1,2, Florian Jug2 1Authors contribut

JugLab 33 Dec 30, 2022
Robust Self-augmentation for NER with Meta-reweighting

Robust Self-augmentation for NER with Meta-reweighting

Lam chi 17 Nov 22, 2022
PyTorch framework, for reproducing experiments from the paper Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks

Implicit Regularization in Hierarchical Tensor Factorization and Deep Convolutional Neural Networks. Code, based on the PyTorch framework, for reprodu

Asaf 3 Dec 27, 2022
El-Gamal on Elliptic Curve (Python)

El-Gamal-on-EC El-Gamal on Elliptic Curve (Python) References: https://docsdrive.com/pdfs/ansinet/itj/2005/299-306.pdf https://arxiv.org/ftp/arxiv/pap

3 May 04, 2022
End-To-End Crowdsourcing

End-To-End Crowdsourcing Comparison of traditional crowdsourcing approaches to a state-of-the-art end-to-end crowdsourcing approach LTNet on sentiment

Andreas Koch 1 Mar 06, 2022
An end-to-end machine learning web app to predict rugby scores (Pandas, SQLite, Keras, Flask, Docker)

Rugby score prediction An end-to-end machine learning web app to predict rugby scores Overview An demo project to provide a high-level overview of the

34 May 24, 2022
NHL 94 AI contests

nhl94-ai The end goals of this project is to: Train Models that play NHL 94 Support AI vs AI contests in NHL 94 Provide an improved AI opponent for NH

Mathieu Poliquin 2 Dec 06, 2021
Code + pre-trained models for the paper Keeping Your Eye on the Ball Trajectory Attention in Video Transformers

Motionformer This is an official pytorch implementation of paper Keeping Your Eye on the Ball: Trajectory Attention in Video Transformers. In this rep

Facebook Research 192 Dec 23, 2022
Official implementation for the paper: Multi-label Classification with Partial Annotations using Class-aware Selective Loss

Multi-label Classification with Partial Annotations using Class-aware Selective Loss Paper | Pretrained models Official PyTorch Implementation Emanuel

99 Dec 27, 2022
Forecasting directional movements of stock prices for intraday trading using LSTM and random forest

Forecasting directional movements of stock-prices for intraday trading using LSTM and random-forest https://arxiv.org/abs/2004.10178 Pushpendu Ghosh,

Pushpendu Ghosh 270 Dec 24, 2022
[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding

[AAAI 2022] Negative Sample Matters: A Renaissance of Metric Learning for Temporal Grounding Official Pytorch implementation of Negative Sample Matter

Multimedia Computing Group, Nanjing University 69 Dec 26, 2022
Official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution"

RealBasicVSR [Paper] This is the official repository of "Investigating Tradeoffs in Real-World Video Super-Resolution, arXiv". This repository contain

Kelvin C.K. Chan 566 Dec 28, 2022
UMPNet: Universal Manipulation Policy Network for Articulated Objects

UMPNet: Universal Manipulation Policy Network for Articulated Objects Zhenjia Xu, Zhanpeng He, Shuran Song Columbia University Robotics and Automation

Columbia Artificial Intelligence and Robotics Lab 33 Dec 03, 2022
BaseCls BaseCls 是一个基于 MegEngine 的预训练模型库，帮助大家挑选或训练出更适合自己科研或者业务的模型结构

BaseCls BaseCls 是一个基于 MegEngine 的预训练模型库，帮助大家挑选或训练出更适合自己科研或者业务的模型结构。 文档地址：https://basecls.readthedocs.io 安装 安装环境 BaseCls 需要 Python = 3.6。 BaseCls 依赖 M

MEGVII Research 28 Dec 23, 2022