Skip to content

This repository is for the paper Metaphor Generation with Conceptual Mappings (ACL 2021).

License

Notifications You must be signed in to change notification settings

Salvia79/acl2021-metaphor-generation-conceptual

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

24 Commits
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Conceptual Metaphor Generation

This repository is for the paper Metaphor Generation with Conceptual Mappings.

Please use the following citation:

@inproceedings{stowe-etal-2021-metaphor,
    title = "Metaphor Generation with Conceptual Mappings",
    author = "Stowe, Kevin  and
      Chakrabarty, Tuhin  and
      Peng, Nanyun  and
      Muresan, Smaranda  and
      Gurevych, Iryna",
    booktitle = "Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2021.acl-long.524",
    doi = "10.18653/v1/2021.acl-long.524",
    pages = "6724--6736",
}

Contact person: Kevin Stowe, stowe@ukp.informatik.tu-darmstadt.de

https://www.ukp.tu-darmstadt.de/

https://www.tu-darmstadt.de/

Don't hesitate to send us an e-mail or report an issue, if something is broken or if you have further questions.

This repository contains experimental software and is published for the sole purpose of giving additional background details on the respective publication.

System Demonstration

Our system demonstration based on the CM-BART model is now available, try it out!

Models

This paper defines two models for metaphor generation based on conceptual mappings: CM-Lex and CM-BART. CM-Lex uses no training data, and works at the word level, while CM-BART is a BART-based seq2seq model.

CM-BART will generally yield better performance, and doesn't require knowing which word to change. If you know which word needs to be changed, CM-Lex may be appropriate.

These models each have their own directory and requirements. See their respective READMEs for more details.

About

This repository is for the paper Metaphor Generation with Conceptual Mappings (ACL 2021).

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 91.0%
  • C 5.4%
  • Cython 3.1%
  • C++ 0.4%
  • Cuda 0.1%
  • Fortran 0.0%