# Fine-Grained Emotional Paraphrasing along Emotion Gradients

arXiv: https://arxiv.org/abs/2212.03297 · HTML: https://mlsanity.com/paper/2212.03297/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 54 references that are in the map.
- First posted on arXiv 30 Oct 2022.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (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)
- [Google's Neural Machine Translation System: Bridging the Gap between Human and Machine Translation](https://mlsanity.com/paper/1609.08144/) (2016)
- [Get To The Point: Summarization with Pointer-Generator Networks](https://mlsanity.com/paper/1704.04368/) (2017)
- [GoEmotions: A Dataset of Fine-Grained Emotions](https://mlsanity.com/paper/2005.00547/) (2020)
- [MAUVE: Measuring the Gap Between Neural Text and Human Text using Divergence Frontiers](https://mlsanity.com/paper/2102.01454/) (2021)
- [PAWS: Paraphrase Adversaries from Word Scrambling](https://mlsanity.com/paper/1904.01130/) (2019)
- [Evaluation of Text Generation: A Survey](https://mlsanity.com/paper/2006.14799/) (2020)
- [Reformulating Unsupervised Style Transfer as Paraphrase Generation](https://mlsanity.com/paper/2010.05700/) (2020)
- [Automatically Neutralizing Subjective Bias in Text](https://mlsanity.com/paper/1911.09709/) (2019)
- [A Continuously Growing Dataset of Sentential Paraphrases](https://mlsanity.com/paper/1708.00391/) (2017)
- [A Deep Generative Framework for Paraphrase Generation](https://mlsanity.com/paper/1709.05074/) (2017)
- [Neural Paraphrase Generation with Stacked Residual LSTM Networks](https://mlsanity.com/paper/1610.03098/) (2016)
- [Syntax-guided Controlled Generation of Paraphrases](https://mlsanity.com/paper/2005.08417/) (2020)
- [Inducing Positive Perspectives with Text Reframing](https://mlsanity.com/paper/2204.02952/) (2022)
- [Paraphrase Generation with Latent Bag of Words](https://mlsanity.com/paper/2001.01941/) (2020)
- [Joint Copying and Restricted Generation for Paraphrase](https://mlsanity.com/paper/1611.09235/) (2016)
- [An Empirical Comparison on Imitation Learning and Reinforcement Learning for Paraphrase Generation](https://mlsanity.com/paper/1908.10835/) (2019)
- [Entailment Relation Aware Paraphrase Generation](https://mlsanity.com/paper/2203.10483/) (2022)

## Abstract (arXiv)

Paraphrase generation, a.k.a. paraphrasing, is a common and important task in natural language processing. Emotional paraphrasing, which changes the emotion embodied in a piece of text while preserving its meaning, has many potential applications, e.g., moderating online dialogues and preventing cyberbullying. We introduce a new task of fine-grained emotional paraphrasing along emotion gradients, that is, altering the emotional intensities of the paraphrases in fine grain following smooth variations in affective dimensions while preserving the meanings of the originals. We propose a framework for addressing this task by fine-tuning text-to-text Transformers through multi-task training. We enhance several widely used paraphrasing corpus by annotating the input and target texts with their fine-grained emotion labels. With these labels, fine-tuning text-to-text Transformers on these corpus entails multi-task training. Evaluations of the fine-tuned Transformers on separate test sets show that including fine-grained emotion labels in the paraphrase task significantly improve the chance of obtaining high-quality paraphrases of the desired emotions, i.e., more than doubling the number of exact matches of desired emotions while achieving consistently better scores in paraphrase metrics such as BLEU, ROGUE, and METEOR.