paper-with-me

홈 › Papers

Persona Extraction Through Semantic Similarity for Emotional Support Conversation Generation

2024-03-07 · Seunghee Han, Se Jin Park, Chae Won Kim, Yong Man Ro

Providing emotional support through dialogue systems is becoming increasingly important in today's world, as it can support both mental health and social interactions in many conversation scenarios. Previous works have shown that using persona is effective for generating empathetic and supportive responses. They have often relied on pre-provided persona rather than inferring them during conversations. However, it is not always possible to obtain a user persona before the conversation begins. To address this challenge, we propose PESS (Persona Extraction through Semantic Similarity), a novel framework that can automatically infer informative and consistent persona from dialogues. We devise completeness loss and consistency loss based on semantic similarity scores. The completeness loss encourages the model to generate missing persona information, and the consistency loss guides the model to distinguish between consistent and inconsistent persona. Our experimental results demonstrate that high-quality persona information inferred by PESS is effective in generating emotionally supportive responses.

📄 PDF Abstract BibTeX arXiv:2403.04212

Code (0)

등록된 구현이 없습니다.

Tasks

Semantic SimilaritySemantic Textual Similarity

Similar Papers 제목 키워드 기반

Modeling Empathic Similarity in Personal Narratives

2023-05-23 · Jocelyn Shen, Maarten Sap, Pedro Colon-Hernandez, Hae Won Park 외

The most meaningful connections between people are often fostered through expression of shared vulnerability and emotional experiences in personal narratives. We introduce a new task of identifying similarity in personal…

RetrievalSemantic SimilaritySemantic Textual Similarity

Decoding Emotional Experiences in Dyadic Conversations of Married Couples: Leveraging Semantic Similarity through Sentence Embedding

2023-09-22 · Chen-Wei Yu, Yun-Shiuan Chuang, Alexandros N. Lotsos, Claudia M. Haase

Recent advancements in Natural Language Processing (NLP) have highlighted the potential of sentence embeddings in measuring semantic similarity (hereafter similarity). Yet, whether this approach can be used to analyze re…

Semantic SimilaritySemantic Textual SimilaritySentenceSentence Embedding+3

Emotional RAG: Enhancing Role-Playing Agents through Emotional Retrieval

2024-10-30 · Le Huang, Hengzhi Lan, Zijun Sun, Chuan Shi 외

As LLMs exhibit a high degree of human-like capability, increasing attention has been paid to role-playing research areas in which responses generated by LLMs are expected to mimic human replies. This has promoted the ex…

RAGResponse GenerationRetrievalRetrieval-augmented Generation+2

From Triggers to Emotions: A CPM-Grounded Appraisal Multi-Agent for Dynamic Emotional Evolution in Persona-Based Dialogue

2026-07-08 · Jingyao Cai, Shuaijun Liu, Abdul Rehman, Yutong Guo 외 arxiv

Large Language Models (LLMs) have substantially advanced persona-based dialogue agents for emotion-sensitive role simulation in healthcare, education, counseling, customer service, and interactive storytelling. However, …

Empathetic Response Generation

Personalized Emotional Intelligence in Generative AI through Symbolic Affective Reasoning

2026-07-12 · Qing Lin, Mengmi Zhang arxiv

Emotional intelligence enables humans to recognize emotions, infer their causes, reason about interventions, and modify their environment to achieve desired affective states. Despite recent advances in artificial intelli…

Emotional Intelligence