Share this page:

Metaphor Generation with Conceptual Mappings

Kevin Stowe, Tuhin Chakrabarty, Nanyun Peng, Smaranda Muresan, and Iryna Gurevych, in ACL, 2021.

Download the full text


Abstract


Bib Entry

@inproceedings{stowe2021metaphor,
  title = {Metaphor Generation with Conceptual Mappings},
  author = {Stowe, Kevin and Chakrabarty, Tuhin and Peng, Nanyun and Muresan, Smaranda and Gurevych, Iryna},
  booktitle = {ACL},
  year = {2021}
}

Related Publications

  1. Metaphor Generation with Conceptual Mappings

    Kevin Stowe, Tuhin Chakrabarty, Nanyun Peng, Smaranda Muresan, and Iryna Gurevych, in ACL, 2021.
    Full Text BibTeX Details
    @inproceedings{stowe2021metaphor,
      title = {Metaphor Generation with Conceptual Mappings},
      author = {Stowe, Kevin and Chakrabarty, Tuhin and Peng, Nanyun and Muresan, Smaranda and Gurevych, Iryna},
      booktitle = {ACL},
      year = {2021}
    }
    
    Details
  2. MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

    Tuhin Chakrabarty, Xurui Zhang, Smaranda Muresan, and Nanyun Peng, in The 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL), 2021.
    Full Text Poster Code Abstract BibTeX Details
    Generating metaphors is a challenging task as it requires a proper understanding of abstract concepts, making connections between unrelated concepts, and deviating from the literal meaning. In this paper, we aim to generate a metaphoric sentence given a literal expression by replacing relevant verbs. Based on a theoretically-grounded connection between metaphors and symbols, we propose a method to automatically construct a parallel corpus by transforming a large number of metaphorical sentences from the Gutenberg Poetry corpus (CITATION) to their literal counterpart using recent advances in masked language modeling coupled with commonsense inference. For the generation task, we incorporate a metaphor discriminator to guide the decoding of a sequence to sequence model fine-tuned on our parallel data to generate high-quality metaphors. Human evaluation on an independent test set of literal statements shows that our best model generates metaphors better than three well-crafted baselines 66% of the time on average. A task-based evaluation shows that human-written poems enhanced with metaphors proposed by our model are preferred 68% of the time compared to poems without metaphors.
    @inproceedings{chakrabarty2021mermaid,
      title = {MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding},
      author = {Chakrabarty, Tuhin and Zhang, Xurui and Muresan, Smaranda and Peng, Nanyun},
      booktitle = {The 2021 Annual Conference of the North American Chapter of the Association for Computational Linguistics (NAACL)},
      presentation_id = {https://underline.io/events/122/sessions/4240/lecture/19642-mermaid-metaphor-generation-with-symbolism-and-discriminative-decoding},
      talk_url = {https://underline.io/events/122/sessions/4240/lecture/19642-mermaid-metaphor-generation-with-symbolism-and-discriminative-decoding},
      year = {2021}
    }
    
    Details