# Nominal Metaphor Generation with Multitask Learning

arXiv: https://arxiv.org/abs/2206.05195 · HTML: https://mlsanity.com/paper/2206.05195/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 39 references that are in the map.
- First posted on arXiv 10 Jun 2022.

## Builds on (most cited first, 12 of 12)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Self-training with Noisy Student improves ImageNet classification](https://mlsanity.com/paper/1911.04252/) (2019)
- [A Diversity-Promoting Objective Function for Neural Conversation Models](https://mlsanity.com/paper/1510.03055/) (2015)
- [COMET: Commonsense Transformers for Automatic Knowledge Graph Construction](https://mlsanity.com/paper/1906.05317/) (2019)
- [SeqGAN: Sequence Generative Adversarial Nets with Policy Gradient](https://mlsanity.com/paper/1609.05473/) (2016)
- [Revisiting Self-Training for Neural Sequence Generation](https://mlsanity.com/paper/1909.13788/) (2019)
- [CPT: A Pre-Trained Unbalanced Transformer for Both Chinese Language Understanding and Generation](https://mlsanity.com/paper/2109.05729/) (2021)
- [CPM: A Large-scale Generative Chinese Pre-trained Language Model](https://mlsanity.com/paper/2012.00413/) (2020)
- [MERMAID: Metaphor Generation with Symbolism and Discriminative Decoding](https://mlsanity.com/paper/2103.06779/) (2021)
- [Lessons from Building Acoustic Models with a Million Hours of Speech](https://mlsanity.com/paper/1904.01624/) (2019)
- [Neural Simile Recognition with Cyclic Multitask Learning and Local Attention](https://mlsanity.com/paper/1912.09084/) (2019)
- ["Love is as Complex as Math": Metaphor Generation System for Social Chatbot](https://mlsanity.com/paper/2001.00733/) (2020)

## Built on by (most cited first, 8 of 8)

- [FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning](https://mlsanity.com/paper/2302.04834/) (2023)
- [Metaphor Detection with Effective Context Denoising](https://mlsanity.com/paper/2302.05611/) (2023)
- [CMDAG: A Chinese Metaphor Dataset with Annotated Grounds as CoT for Boosting Metaphor Generation](https://mlsanity.com/paper/2402.13145/) (2024)
- [The Secret of Metaphor on Expressing Stronger Emotion](https://mlsanity.com/paper/2301.13042/) (2023)
- [Finding Challenging Metaphors that Confuse Pretrained Language Models](https://mlsanity.com/paper/2401.16012/) (2024)
- [CERD: A Comprehensive Chinese Rhetoric Dataset for Rhetorical Understanding and Generation in Essays](https://mlsanity.com/paper/2409.19691/) (2024)
- [Modeling Comparative Logical Relation with Contrastive Learning for Text Generation](https://mlsanity.com/paper/2406.09095/) (2024)
- [Towards High-Level Semantic Intelligence](https://mlsanity.com/paper/2607.24082/) (2026)

## Abstract (arXiv)

Metaphor generation is a challenging task which can impact many downstream tasks such as improving user satisfaction with dialogue systems and story generation. This paper tackles the problem of Chinese nominal metaphor generation by introducing a multitask metaphor generation framework with self-training and metaphor identification mechanisms. Self-training addresses the data scarcity issue of metaphor datasets. That is, instead of solely relying on labelled metaphor datasets which are usually small in size, self-training helps identify potential metaphors from a large-scale unlabelled corpus for metaphor generation. The metaphor weighting mechanism enables our model to focus on the metaphor-related parts of the input (e.g., the comparison of the metaphor and comparator) during model learning and thus improves the metaphoricity of the generated metaphors. Our model is trained on an annotated corpus consisting of 6.3k sentences that contain diverse metaphorical expressions. Experimental results show that our model is able to generate metaphors with better readability and creativity compared to the baseline models, even in the situation where training data is insufficient.