This repository contains the code for: RerrFact model for SciVer shared task

Last update: May 22, 2022

Related tags

Deep Learning RerrFact

Overview

RerrFact

This repository contains the code for: RerrFact model for SciVer shared task.

Setup for Inference

1. Download SciFact database

Download the SciFact database from here.

2. Installing requirements

Install the requirements using the following command for abstract retrieval and rationale selection module.

pip install -r abstract,rationale_requirements.txt

Install the requirements using the following command for label prediction module.

pip install -r label_requirements.txt

3. Download trained models

Download the trained models using this link.

4. Using pre-trained models

Abstract Retrieval

python ./inference/abstract-retrieval.py \
--corpus ./data/corpus.jsonl \
--dataset ./data/claims_test.jsonl \
--model ./saved_models/abstract_retrieval_model_here \
--output ./prediction/abstract_retrieval_test_predictions.jsonl

Rationale Selection

python ./inference/rationale-selection.py \
--corpus ./data/corpus.jsonl \
--dataset ./data/claims_test.jsonl \
--abstract ./prediction/abstract_retrieval_test_predictions.jsonl \
--model ./saved_models/rationale_selection_model_here \
--output ./prediction/

Label Prediction

python inference/label-prediction.py \
--corpus '/data/corpus.jsonl' \
--dataset './data/claims_test.jsonl' \
--rationale-selection './prediction/rationale_selection.jsonl' \
--model_n './saved_models/neutral_classifer_here' \
--model_s './saved_models/support_classifier_here' \
--output './prediction/label_pred_test.jsonl'

Retrain models

Refer to training/Abstract-retrieval.ipynb for training abstract retrieval module.

Refer to training/Rationale-selection.ipynb for training rationale selection module.

Refer to training/Label-prediction.ipynb for training label prediction module.

This repository contains the code for: RerrFact model for SciVer shared task

Related tags

Overview

RerrFact

Setup for Inference

1. Download SciFact database

2. Installing requirements

3. Download trained models

4. Using pre-trained models

Retrain models

Owner

Ashish Rana

Code and models for ICCV2021 paper "Robust Object Detection via Instance-Level Temporal Cycle Confusion".

simple artificial intelligence utilities

Minecraft agent to farm resources using reinforcement learning

Code accompanying the paper "Wasserstein GAN"

A flexible tool for creating, organizing, and sharing visualizations of live, rich data. Supports Torch and Numpy.

Unsupervised Representation Learning by Invariance Propagation

TraND: Transferable Neighborhood Discovery for Unsupervised Cross-domain Gait Recognition.

A Light CNN for Deep Face Representation with Noisy Labels

[SIGGRAPH 2020] Attribute2Font: Creating Fonts You Want From Attributes

NaijaSenti is an open-source sentiment and emotion corpora for four major Nigerian languages

This package implements THOR: Transformer with Stochastic Experts.

[Nature Machine Intelligence' 21] "Advancing COVID-19 Diagnosis with Privacy-Preserving Collaboration in Artificial Intelligence"

Official PyTorch implementation of MX-Font (Multiple Heads are Better than One: Few-shot Font Generation with Multiple Localized Experts)

SurvITE: Learning Heterogeneous Treatment Effects from Time-to-Event Data

A U-Net combined with a variational auto-encoder that is able to learn conditional distributions over semantic segmentations.

Federated Learning Based on Dynamic Regularization

An interactive DNN Model deployed on web that predicts the chance of heart failure for a patient with an accuracy of 98%

Official implementation of "Open-set Label Noise Can Improve Robustness Against Inherent Label Noise" (NeurIPS 2021)

The implementation for the SportsCap (IJCV 2021)

This repo. is an implementation of ACFFNet, which is accepted for in Image and Vision Computing.