Skip to content

Dataset and Code for Generating Faithful and Salient Text from Multimodal Data (INLG 2024) paper.

Notifications You must be signed in to change notification settings

TahsinaHashem/FaithD2T

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Dataset and Code for Generating Faithful and Salient Text from Multimodal Data (INLG 2024) paper.

Dataset Download Link

Please download the Real-estate House Dataset from here.

Training & Evaluation

The scripts for training and evaluation are in the main directory.

Training

#Finetune blip2-flan-t5-xl model and save checkpoint
python trainPart1.py
python trainPart2.py

Evaluation

#Perform inference on test data
python evalPart1.py
python evalPart2.py

Cite

If you find this work useful for your research, please consider citing.

@inproceedings{hashem2024generating,
  author    = "Hashem, Tahsina and Wang, Weiqing and Wijaya, Derry Tanti and Ali, Mohammed Eunus and Li, Yuan-Fang"
  title     = "Generating Faithful and Salient Text from Multimodal Data",
  booktitle = "INLG",
  year      = "2024",
}

Acknowledgements

This implementation is based on the code provided by huggingface/peft

About

Dataset and Code for Generating Faithful and Salient Text from Multimodal Data (INLG 2024) paper.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages