Skip to content
/ MFN Public

Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos

Notifications You must be signed in to change notification settings

forkarinda/MFN

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

21 Commits
 
 
 
 
 
 
 
 

Repository files navigation

MFN

Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos

Data

You can download the extracted ASR transcription from google drive.

Start

Please go to folder MF_RNN or MF_transformer to start the experiment.

Evaluation

Please use the nmtpytorch evaluation library suggested by the How2 Challenge, which includes BLEU (1, 2, 3, 4), ROUGE-L, METEOR, and CIDEr evaluation metrics.

As an alternative, nlg-eval evaluation library can obtain the same evaluation score as nmtpytorch.

In addition, a ROUGE evaluation library can be used to calculate the ROUGE series (ROUGE-N, ROUGE-L, ROUGE-W) score.

Acknowledgement

We are very grateful that the code is based on nmtpytorch, fairseq, and machine-translation.

About

Multistage Fusion with Forget Gate for Multimodal Summarization in Open-Domain Videos

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published