Log In Sign Up

MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding

by   Tuhin Chakrabarty, et al.

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. 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 human-written poems enhanced with metaphors proposed by our model are preferred 68


Generating similes <effortlessly> like a Pro: A Style Transfer Approach for Simile Generation

Literary tropes, from poetry to stories, are at the crux of human imagin...

Lexically-constrained Text Generation through Commonsense Knowledge Extraction and Injection

Conditional text generation has been a challenging task that is yet to s...

CommonGen: A Constrained Text Generation Dataset Towards Generative Commonsense Reasoning

Rational humans can generate sentences that cover a certain set of conce...

Generating Commonsense Explanation by Extracting Bridge Concepts from Reasoning Paths

Commonsense explanation generation aims to empower the machine's sense-m...

Improving Large-scale Paraphrase Acquisition and Generation

This paper addresses the quality issues in existing Twitter-based paraph...

Paraphrase Generation with Deep Reinforcement Learning

Automatic generation of paraphrases for a given sentence is an important...

Generating Coherent and Diverse Slogans with Sequence-to-Sequence Transformer

Previous work in slogan generation focused on generating novel slogans b...