Answering Open-Domain Questions of Varying Reasoning Steps from Text

Related tags

Deep LearningIRRR
Overview

IRRR

This repository contains the authors' implementation of the Iterative Retriever, Reader, and Reranker (IRRR) model in the EMNLP 2021 paper "Answering Open-Domain Questions of Varying Reasoning Steps from Text".

IRRR pipeline

Run prediction on BeerQA

Setting up

Checkout the code from our repository using

git clone https://github.com/beerqa/IRRR.git

This repo requires Python 3.6. Please check your shell environment's python before proceeding. To use ElasticSearch, make sure you also install Java Development Kit (JDK) version 8.

The setup script will download all required dependencies (python requirements, data, models, etc.) required to run the IRRR pipeline end-to-end. Before running this script, make sure you have the Unix utility wget (which can be installed through anaconda as well as other common package managers). Along the way, it will also start running Elasticsearch and index the Wikipedia corpus locally.

Note: This might take a while to finish and requires a large amount of disk space, so it is strongly recommended that you run this on a machine with at least 100GB of free disk space.

bash setup.sh

Run prediction

Here is a quick example for running prediction using our trained model on the BeerQA dataset. It will take hours depending on the number of retrieved passages at each iteration. It requires up-to 100GB of storage for storing intermediate files when are large number of passages are retrieved at each reasoning step

bash scripts/predict_dynamic_hops.sh PREDICT_OUTPUT_PATH \
                                     ./data/beerqa/beerqa_dev_v1.0.json \
				     MODEL_OUTPUT_PATH \
				     NUM_PASSAGES_AT_EACH_ITERATION \
				     MAX_ITERATION

Evaluate the prediction

Once the prediction has been made, you can use the following command to evaluate the output

python utils/eval_beerqa.py ./data/beerqa/beerqa_dev_v1.0.json \
                            PREDICT_OUTPUT_PATH/answer_predictions.json

Citation

If you use IRRR in your work, please consider citing our paper

@inproceedings{qi2021answering,
  title={Answering Open-Domain Questions of Varying Reasoning Steps from Text},
  author = {Qi, Peng and Lee, Haejun and Sido, Oghenetegiri "TG" and Manning, Christopher D.},
  booktitle = {Empirical Methods for Natural Language Processing ({EMNLP})},
  year = {2021}
}

License

All work contained in this package is licensed under the Apache License, Version 2.0. See the included LICENSE file.

PyTorch code for Composing Partial Differential Equations with Physics-Aware Neural Networks

FInite volume Neural Network (FINN) This repository contains the PyTorch code for models, training, and testing, and Python code for data generation t

Cognitive Modeling 20 Dec 18, 2022
Single-Stage Instance Shadow Detection with Bidirectional Relation Learning (CVPR 2021 Oral)

Single-Stage Instance Shadow Detection with Bidirectional Relation Learning (CVPR 2021 Oral) Tianyu Wang*, Xiaowei Hu*, Chi-Wing Fu, and Pheng-Ann Hen

Steve Wong 51 Oct 20, 2022
DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs

DeepI2I: Enabling Deep Hierarchical Image-to-Image Translation by Transferring from GANs Abstract: Image-to-image translation has recently achieved re

yaxingwang 23 Apr 14, 2022
To provide 100 JAX exercises over different sections structured as a course or tutorials to teach and learn for beginners, intermediates as well as experts

JaxTon 💯 JAX exercises Mission 🚀 To provide 100 JAX exercises over different sections structured as a course or tutorials to teach and learn for beg

Rohan Rao 512 Jan 01, 2023
Code for the tech report Toward Training at ImageNet Scale with Differential Privacy

Differentially private Imagenet training Code for the tech report Toward Training at ImageNet Scale with Differential Privacy by Alexey Kurakin, Steve

Google Research 29 Nov 03, 2022
DL course co-developed by YSDA, HSE and Skoltech

Deep learning course This repo supplements Deep Learning course taught at YSDA and HSE @fall'21. For previous iteration visit the spring21 branch. Lec

Yandex School of Data Analysis 1.3k Dec 30, 2022
Deep ViT Features as Dense Visual Descriptors

dino-vit-features [paper] [project page] Official implementation of the paper "Deep ViT Features as Dense Visual Descriptors". We demonstrate the effe

Shir Amir 113 Dec 24, 2022
Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pretrained SOTA Deep Learning models, callbacks and more for research and production with PyTorch Lightning and PyTorch

Pytorch Lightning 1.4k Jan 01, 2023
An unofficial implementation of "Unpaired Image Super-Resolution using Pseudo-Supervision." CVPR2020

UnpairedSR An unofficial implementation of "Unpaired Image Super-Resolution using Pseudo-Supervision." CVPR2020 turn RCAN(modified) -- xmodel(xilinx

JiaKui Hu 10 Oct 28, 2022
A hobby project which includes a hand-gesture based virtual piano using a mobile phone camera and OpenCV library functions

Overview This is a hobby project which includes a hand-gesture controlled virtual piano using an android phone camera and some OpenCV library. My moti

Abhinav Gupta 1 Nov 19, 2021
ToFFi - Toolbox for Frequency-based Fingerprinting of Brain Signals

ToFFi Toolbox This repository contains "before peer review" version of the software related to the preprint of the publication ToFFi - Toolbox for Fre

4 Aug 31, 2022
Text-to-Image generation

Generate vivid Images for Any (Chinese) text CogView is a pretrained (4B-param) transformer for text-to-image generation in general domain. Read our p

THUDM 1.3k Dec 29, 2022
This is a TensorFlow implementation for C2-Rec

This is a TensorFlow implementation for C2-Rec We refer to the repo SASRec. Requirements requirement.txt Datasets This repo includes Amazon Beauty dat

7 Nov 14, 2022
Using modified BiSeNet for face parsing in PyTorch

face-parsing.PyTorch Contents Training Demo References Training Prepare training data: -- download CelebAMask-HQ dataset -- change file path in the pr

zll 1.6k Jan 08, 2023
Propose a principled and practically effective framework for unsupervised accuracy estimation and error detection tasks with theoretical analysis and state-of-the-art performance.

Detecting Errors and Estimating Accuracy on Unlabeled Data with Self-training Ensembles This project is for the paper: Detecting Errors and Estimating

Jiefeng Chen 13 Nov 21, 2022
AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations

AugLy is a data augmentations library that currently supports four modalities (audio, image, text & video) and over 100 augmentations. Each modality’s augmentations are contained within its own sub-l

Facebook Research 4.6k Jan 09, 2023
[ACL-IJCNLP 2021] Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning

CLNER The code is for our ACL-IJCNLP 2021 paper: Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning CLNER is a

71 Dec 08, 2022
Fast and customizable reconnaissance workflow tool based on simple YAML based DSL.

Fast and customizable reconnaissance workflow tool based on simple YAML based DSL, with support of notifications and distributed workload of that work

Américo Júnior 3 Mar 11, 2022
A self-supervised learning framework for audio-visual speech

AV-HuBERT (Audio-Visual Hidden Unit BERT) Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction Robust Self-Supervised A

Meta Research 431 Jan 07, 2023