Skip to content

[NAACL2018] Entity Commonsense Representation for Neural Abstractive Summarization

Notifications You must be signed in to change notification settings

rktamplayo/Entity2Topic

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

8 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Entity2Topic

Entity Commonsense Representation for Neural Abstractive Summarization

This TensorFlow code was used in the experiments of the research paper

Reinald Kim Amplayo*, Seonjae Lim* and Seung-won Hwang. Entity Commonsense Representation for Neural Abstractive Summarization. NAACL, 2018.

* Authors have equal contributions

You will need the following data saved in a separate data folder:

To run the code, several parameters are needed to be set in the src/summarization.py. Refer to our paper to determine the recommended values.

To train the model, execute the following code:

python script/train.py

Similarly, to test the model, execute the following code (although test will automatically come after training is done):

python script/test.py

To cite the paper/code, please use this BibTex:

@inproceedings{amplayo2018entity,
	Author = {Reinald Kim Amplayo and Seonjae Lim and Seung-won Hwang},
	Booktitle = {NAACL},
	Location = {New Orleans, LA},
	Year = {2018},
	Title = {Entity Commonsense Representation for Neural Abstractive Summarization},
}

If you have questions, send me an email: rktamplayo at yonsei dot ac dot kr