Code to reproduce the results in "Visually Grounded Reasoning across Languages and Cultures", EMNLP 2021.

Last update: Nov 15, 2022

Related tags

Overview

marvl-code [WIP]

This is the implementation of the approaches described in the paper:

Fangyu Liu*, Emanuele Bugliarello*, Edoardo M. Ponti, Siva Reddy, Nigel Collier and Desmond Elliott. Visually Grounded Reasoning over Languages and Cultures. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing (EMNLP), Nov 2021.

We provide the pretrained models and the code for reproducing our results.

The textual data and the preprocessed visual features are available in marvl-data.

The code will also be integrated into VOLTA, upon which our repository was origally built.

Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Coming soon!

ToxiChat Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Install depen

11 Jan 1, 2023

The code repository for EMNLP 2021 paper "Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization".

Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization [Paper] accepted at the EMNLP 2021: Vision Guided Genera

42 Jan 7, 2023

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

MultiModal-InfoMax This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Informa

Deep Cognition and Language Research (DeCLaRe) Lab

89 Dec 26, 2022

Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Contra-OOD Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers. Requirements PyTorch Transformers datasets

27 Oct 28, 2022

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Text-AutoAugment (TAA) This repository contains the code for our paper Text AutoAugment: Learning Compositional Augmentation Policy for Text Classific

105 Jan 3, 2023

Code and data for "Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning" (EMNLP 2021).

GD-VCR Code for Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning (EMNLP 2021). Research Questions and Aims: How well can a model perform o

24 Oct 13, 2022

Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

16 Jul 16, 2022

PyTorch code for EMNLP 2021 paper: Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

Don’t be Contradicted with Anything!CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System This repository contains the PyTorch im

25 Sep 6, 2022

PyTorch code for EMNLP 2021 paper: Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

12 Sep 26, 2021

Comments

Is img_segment_ids used for evaluation?

Hi @e-bug Is this useful information for the model? https://github.com/marvl-challenge/marvl-code/blob/master/volta/volta/datasets/marvl_dataset.py#L163 I saw you not using it

opened by lonestar234028 2
Excuse me, why can't I see the code?

Thank you very much for your interesting work, but after I found this website according to the link in the paper, I did not see the relevant code. Should I go to another website to get the code?

opened by Peng-weil 2
different results from iglue

Hello, I notice that the average result of zero-shot. in marvl-code mUNITER 54.0, xUNITER. 56.1 is higher than your recent work iglue mUNITER 53.72 xUNITER 54.59 . Especially for xUNITER ( 54.59 is about 1.5 points lower that 56.1) I reproduced your experiment with marvl-code Repository and the results are close to iglue . Can you give me some advice to imporve the results ? Or I should regard the iglue as baseline ?

opened by lizhiustc 1

Owner

GitHub

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

Transformer Based Multi-Source Domain Adaptation Dustin Wright and Isabelle Augenstein To appear in EMNLP 2020. Read the preprint: https://arxiv.org/a

36 Dec 5, 2022

Code to reproduce the results for Compositional Attention: Disentangling Search and Retrieval.

Compositional-Attention This repository contains the official implementation for the paper Compositional Attention: Disentangling Search and Retrieval

17 Oct 23, 2021

Code to reproduce the results in the paper "Tensor Component Analysis for Interpreting the Latent Space of GANs".

Tensor Component Analysis for Interpreting the Latent Space of GANs [ paper | project page ] Code to reproduce the results in the paper "Tensor Compon

4 Jun 17, 2022

Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Code To run: python runner.py new --save <SAVE_NAME> --data <PATH_TO_DATA_DIR> --dataset <DATASET> --model <model_name> [options] --n 1000 - train - t

5 Dec 12, 2022

Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"

gtn_applications An applications library using GTN. Current examples include: Offline handwriting recognition Automatic speech recognition Installing

68 Dec 29, 2022

Code to reproduce the results in "Visually Grounded Reasoning across Languages and Cultures", EMNLP 2021.

Related tags

Overview

marvl-code [WIP]

You might also like...

Code and data for the EMNLP 2021 paper "Just Say No: Analyzing the Stance of Neural Dialogue Generation in Offensive Contexts". Coming soon!

The code repository for EMNLP 2021 paper "Vision Guided Generative Pre-trained Language Models for Multimodal Abstractive Summarization".

This repository contains the official implementation code of the paper Improving Multimodal Fusion with Hierarchical Mutual Information Maximization for Multimodal Sentiment Analysis, accepted at EMNLP 2021.

Code for EMNLP 2021 paper Contrastive Out-of-Distribution Detection for Pretrained Transformers.

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

Code and data for "Broaden the Vision: Geo-Diverse Visual Commonsense Reasoning" (EMNLP 2021).

Code and data to accompany the camera-ready version of "Cross-Attention is All You Need: Adapting Pretrained Transformers for Machine Translation" in EMNLP 2021

PyTorch code for EMNLP 2021 paper: Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

PyTorch code for EMNLP 2021 paper: Don't be Contradicted with Anything! CI-ToD: Towards Benchmarking Consistency for Task-oriented Dialogue System

Comments

Is img_segment_ids used for evaluation?

Excuse me, why can't I see the code?

different results from iglue

Owner

Code to reproduce the experiments in the paper "Transformer Based Multi-Source Domain Adaptation" (EMNLP 2020)

Code to reproduce the results for Compositional Attention: Disentangling Search and Retrieval.

Code to reproduce the results in the paper "Tensor Component Analysis for Interpreting the Latent Space of GANs".

Code to reproduce the experiments from our NeurIPS 2021 paper " The Limitations of Large Width in Neural Networks: A Deep Gaussian Process Perspective"

Applications using the GTN library and code to reproduce experiments in "Differentiable Weighted Finite-State Transducers"

Code reproduce for paper "Vehicle Re-identification with Viewpoint-aware Metric Learning"

This repo will contain code to reproduce and build upon understanding transfer learning

PyTorch Implementation of Fully Convolutional Networks. (Training code to reproduce the original result is available.)

Code to reproduce experiments in the paper "Explainability Requires Interactivity".

Source code and notebooks to reproduce experiments and benchmarks on Bias Faces in the Wild (BFW).