Emotion and Sentiment Guided Paraphrasing
This work addresses the problem of generating emotionally nuanced paraphrases for applications like moderating online dialogues, though it is incremental as it builds on existing paraphrasing methods.
The paper tackles the task of fine-grained emotional paraphrasing by altering emotional intensities along gradients while preserving meaning, and shows that including fine-grained emotion labels improves paraphrase quality with better BLEU, ROUGE, and METEOR scores.
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, including 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-grained settings following smooth variations in affective dimensions while preserving the meaning of the original text. We reconstruct several widely used paraphrasing datasets by augmenting the input and target texts with their fine-grained emotion labels. Then, we propose a framework for emotion and sentiment guided paraphrasing by leveraging pre-trained language models for conditioned text generation. Extensive evaluation of the fine-tuned models suggests that including fine-grained emotion labels in the paraphrase task significantly improves the likelihood of obtaining high-quality paraphrases that reflect the desired emotions while achieving consistently better scores in paraphrase metrics such as BLEU, ROUGE, and METEOR.