paper-with-me

Papers

Emotion and Sentiment Guided Paraphrasing

2023-06-08 · Justin J. Xie, Ameeta Agrawal

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.

📄 PDF Abstract BibTeX arXiv:2306.05556

Code (0)

등록된 구현이 없습니다.

Tasks

Paraphrase GenerationText Generation

Similar Papers 제목 키워드 기반

Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection

2025-08-09 · Siyuan Li, Xi Lin, Guangyan Li, Zehao Liu 외 arxiv

The rapid advancement of large language models (LLMs) has resulted in increasingly sophisticated AI-generated content, posing significant challenges in distinguishing LLM-generated text from human-written language. Exist…

Fine-Grained Emotional Paraphrasing along Emotion Gradients

2022-10-30 · Justin Xie

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 m…

Paraphrase Generation

MS-Mix: Sentiment-Guided Adaptive Augmentation for Multimodal Sentiment Analysis

2025-10-13 · Hongyu Zhu, Lin Chen, Xin Jin, Mingsheng Shang arxiv

Multimodal Sentiment Analysis (MSA) integrates complementary features from text, video, and audio for robust emotion understanding in human interactions. However, models suffer from severe data scarcity and high annotati…

Multimodal Sentiment AnalysisSemantic Similarity

EmoLat: Text-driven Image Sentiment Transfer via Emotion Latent Space

2026-01-17 · Jing Zhang, Bingjie Fan, Jixiang Zhu, Zhe Wang arxiv

We propose EmoLat, a novel emotion latent space that enables fine-grained, text-driven image sentiment transfer by modeling cross-modal correlations between textual semantics and visual emotion features. Within EmoLat, a…

Using Pivot-Based Paraphrasing and Sentiment Profiles to Improve a Subjectivity Lexicon for Essay Data

2013-01-01 · TACL 2013 1 · Beata Beigman Klebanov, Nitin Madnani, Jill Burstein

We demonstrate a method of improving a seed sentiment lexicon developed on essay data by using a pivot-based paraphrasing system for lexical expansion coupled with sentiment profile enrichment using crowdsourcing. Profil…

General ClassificationSentenceSentiment Analysis