liqiangjing / team

TEAM

This repo holds codes of the paper: ''Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation '' published on the conference ACL 2023. https://aclanthology.org/2023.acl-long.635/

Related Data

You can downloand caption data, knowledge, objects and and adjacent matrix via the link: https://drive.google.com/drive/folders/13vuYwJzGEnvV3r-gJxihVNjvIiuGrO6q?usp=share_link.

Run

python bsl_train.py

Citation

If you find this repo useful in your research works, please consider citing:

@inproceedings{jing2023msgm,
author = {Liqiang Jing and Xuemeng Song and Kun Ouyang and Mengzhao Jia and Liqiang Nie},
title = {Multi-source Semantic Graph-based Multimodal Sarcasm Explanation Generation},
year = {2023},
publisher = {Association for Computational Linguistics},
booktitle = {Proceedings of the Annual Meeting of the Association for Computational Linguistics},
pages = {11349--11361}
}

team's Issues

Faster RCNN

Hello
Could you provide an inference-ready implementation of the Faster-RCNN you used? I want to run some experiments and would be quite grateful if you could provide the same since you have already used the same for your paper.
Thank you

资源请求

能提供一下生成pkl文件的源码，谢谢！

img file

Thanks for your code sharing. I want to run the code project, but I can't find the data set of the picture. Is it missing from the upload, or I can't find it here.

Where can I get ConceptNet.json

Hello , thanks for your great work, I am wondering that how to get the ConceptNet.json in your code:

concept_dict = json.load(open("ConceptNet.json", "r", encoding="utf-8"))
FileNotFoundError: [Errno 2] No such file or directory: 'ConceptNet.json'

How can I run this code on Google Colab?

Hello, I am an undergraduate student researcher trying to implement your code on Google Colab. However, I keep running into the following error:

usage: colab_kernel_launcher.py [--help] [--hydra-help] [--version]
                                [--cfg {job,hydra,all}] [--resolve]
                                [--package PACKAGE] [--run] [--multirun]
                                [--shell-completion]
                                [--config-path CONFIG_PATH]
                                [--config-name CONFIG_NAME]
                                [--config-dir CONFIG_DIR]
                                [--experimental-rerun EXPERIMENTAL_RERUN]
                                [--info [{all,config,defaults,defaults-tree,plugins,searchpath}]]
                                [overrides ...]
colab_kernel_launcher.py: error: unrecognized arguments: -f

I have tried implementing the code on my local machine and it is working fine. I would be grateful if you could guide me on how to do the same on Google Colab.

Regarding the Faster-RCNN implementation proposed in the research paper

I am an undergraduate student and am trying to implement your paper as a part of my research. Your paper states that your model utilises a Faster-RCNN for best performance. However, the code given by you makes use of a vision transformer (from the ablation study is my guess). Could you kindly provide the code for the model using the Faster-RCNN?
Thank you.