# MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

arXiv: https://arxiv.org/abs/2103.06779 · HTML: https://mlsanity.com/paper/2103.06779/

## Key facts

- Cited by 49 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 55 references that are in the map.
- First posted on arXiv 11 Mar 2021.

## Builds on (most cited first, 17 of 17)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Deep contextualized word representations](https://mlsanity.com/paper/1802.05365/) (2018)
- [fairseq: A Fast, Extensible Toolkit for Sequence Modeling](https://mlsanity.com/paper/1904.01038/) (2019)
- [Hierarchical Neural Story Generation](https://mlsanity.com/paper/1805.04833/) (2018)
- [ConceptNet 5.5: An Open Multilingual Graph of General Knowledge](https://mlsanity.com/paper/1612.03975/) (2016)
- [Universal Adversarial Triggers for Attacking and Analyzing NLP](https://mlsanity.com/paper/1908.07125/) (2019)
- [The Woman Worked as a Babysitter: On Biases in Language Generation](https://mlsanity.com/paper/1909.01326/) (2019)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [Why We Need New Evaluation Metrics for NLG](https://mlsanity.com/paper/1707.06875/) (2017)
- [Learning to Write with Cooperative Discriminators](https://mlsanity.com/paper/1805.06087/) (2018)
- [Content Planning for Neural Story Generation with Aristotelian Rescoring](https://mlsanity.com/paper/2009.09870/) (2020)
- [Neural Metaphor Detection in Context](https://mlsanity.com/paper/1808.09653/) (2018)
- [Metaphoric Paraphrase Generation](https://mlsanity.com/paper/2002.12854/) (2020)

## Built on by (most cited first, 30 of 49)

- [Symbolic Knowledge Distillation: from General Language Models to Commonsense Models](https://mlsanity.com/paper/2110.07178/) (2021)
- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [Sparks: Inspiration for Science Writing using Language Models](https://mlsanity.com/paper/2110.07640/) (2021)
- [AI Suggestions Homogenize Writing Toward Western Styles and Diminish Cultural Nuances](https://mlsanity.com/paper/2409.11360/) (2024)
- [Shaping Human-AI Collaboration: Varied Scaffolding Levels in Co-writing with Language Models](https://mlsanity.com/paper/2402.11723/) (2024)
- [MemeCap: A Dataset for Captioning and Interpreting Memes](https://mlsanity.com/paper/2305.13703/) (2023)
- [It's not Rocket Science : Interpreting Figurative Language in Narratives](https://mlsanity.com/paper/2109.00087/) (2021)
- [Metaphor Generation with Conceptual Mappings](https://mlsanity.com/paper/2106.01228/) (2021)
- [I Spy a Metaphor: Large Language Models and Diffusion Models Co-Create Visual Metaphors](https://mlsanity.com/paper/2305.14724/) (2023)
- [MetaCLUE: Towards Comprehensive Visual Metaphors Research](https://mlsanity.com/paper/2212.09898/) (2022)
- [Figurative Language in Recognizing Textual Entailment](https://mlsanity.com/paper/2106.01195/) (2021)
- [Fluid Transformers and Creative Analogies: Exploring Large Language Models' Capacity for Augmenting Cross-Domain Analogical Creativity](https://mlsanity.com/paper/2302.12832/) (2023)
- [HypoGen: Hyperbole Generation with Commonsense and Counterfactual Knowledge](https://mlsanity.com/paper/2109.05097/) (2021)
- [AmbiPun: Generating Humorous Puns with Ambiguous Context](https://mlsanity.com/paper/2205.01825/) (2022)
- [ePiC: Employing Proverbs in Context as a Benchmark for Abstract Language Understanding](https://mlsanity.com/paper/2109.06838/) (2021)
- [MOVER: Mask, Over-generate and Rank for Hyperbole Generation](https://mlsanity.com/paper/2109.07726/) (2021)
- [Machine-in-the-Loop Rewriting for Creative Image Captioning](https://mlsanity.com/paper/2111.04193/) (2021)
- [CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation](https://mlsanity.com/paper/2402.13145/) (2024)
- [MMTE: Corpus and Metrics for Evaluating Machine Translation Quality of Metaphorical Language](https://mlsanity.com/paper/2406.13698/) (2024)
- [Nominal Metaphor Generation with Multitask Learning](https://mlsanity.com/paper/2206.05195/) (2022)
- [Metaphor and Large Language Models: When Surface Features Matter More than Deep Understanding](https://mlsanity.com/paper/2507.15357/) (2025)
- [Creativity in AI: Progresses and Challenges](https://mlsanity.com/paper/2410.17218/) (2024)
- [PANCETTA: Phoneme Aware Neural Completion to Elicit Tongue Twisters Automatically](https://mlsanity.com/paper/2209.06275/) (2022)
- [Controllable Text Generation for Open-Domain Creativity and Fairness](https://mlsanity.com/paper/2209.12099/) (2022)
- [Language Models as Critical Thinking Tools: A Case Study of Philosophers](https://mlsanity.com/paper/2404.04516/) (2024)
- [Generating Harder Cross-document Event Coreference Resolution Datasets using Metaphoric Paraphrasing](https://mlsanity.com/paper/2407.11988/) (2024)
- [Probing Simile Knowledge from Pre-trained Language Models](https://mlsanity.com/paper/2204.12807/) (2022)
- [Exploring Euphemism Detection in Few-Shot and Zero-Shot Settings](https://mlsanity.com/paper/2210.12926/) (2022)
- [Creative Data Generation: A Review Focusing on Text and Poetry](https://mlsanity.com/paper/2305.08493/) (2023)
- [Construction Artifacts in Metaphor Identification Datasets](https://mlsanity.com/paper/2311.00790/) (2023)

## Abstract (arXiv)

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 (Jacobs, 2018) 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.