STICKERCONV: Generating Multimodal Empathetic Responses from Scratch
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866912160929546240 |
|---|---|
| author | Zhang, Yiqun Kong, Fanheng Wang, Peidong Sun, Shuang Wang, Lingshuai Feng, Shi Wang, Daling Zhang, Yifei Song, Kaisong |
| author_facet | Zhang, Yiqun Kong, Fanheng Wang, Peidong Sun, Shuang Wang, Lingshuai Feng, Shi Wang, Daling Zhang, Yifei Song, Kaisong |
| contents | Stickers, while widely recognized for enhancing empathetic communication in online interactions, remain underexplored in current empathetic dialogue research, notably due to the challenge of a lack of comprehensive datasets. In this paper, we introduce the Agent for STICKERCONV (Agent4SC), which uses collaborative agent interactions to realistically simulate human behavior with sticker usage, thereby enhancing multimodal empathetic communication. Building on this foundation, we develop a multimodal empathetic dialogue dataset, STICKERCONV, comprising 12.9K dialogue sessions, 5.8K unique stickers, and 2K diverse conversational scenarios. This dataset serves as a benchmark for multimodal empathetic generation. To advance further, we propose PErceive and Generate Stickers (PEGS), a multimodal empathetic response generation framework, complemented by a comprehensive set of empathy evaluation metrics based on LLM. Our experiments demonstrate PEGS's effectiveness in generating contextually relevant and emotionally resonant multimodal empathetic responses, contributing to the advancement of more nuanced and engaging empathetic dialogue systems. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_01679 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | STICKERCONV: Generating Multimodal Empathetic Responses from Scratch Zhang, Yiqun Kong, Fanheng Wang, Peidong Sun, Shuang Wang, Lingshuai Feng, Shi Wang, Daling Zhang, Yifei Song, Kaisong Computation and Language Artificial Intelligence Stickers, while widely recognized for enhancing empathetic communication in online interactions, remain underexplored in current empathetic dialogue research, notably due to the challenge of a lack of comprehensive datasets. In this paper, we introduce the Agent for STICKERCONV (Agent4SC), which uses collaborative agent interactions to realistically simulate human behavior with sticker usage, thereby enhancing multimodal empathetic communication. Building on this foundation, we develop a multimodal empathetic dialogue dataset, STICKERCONV, comprising 12.9K dialogue sessions, 5.8K unique stickers, and 2K diverse conversational scenarios. This dataset serves as a benchmark for multimodal empathetic generation. To advance further, we propose PErceive and Generate Stickers (PEGS), a multimodal empathetic response generation framework, complemented by a comprehensive set of empathy evaluation metrics based on LLM. Our experiments demonstrate PEGS's effectiveness in generating contextually relevant and emotionally resonant multimodal empathetic responses, contributing to the advancement of more nuanced and engaging empathetic dialogue systems. |
| title | STICKERCONV: Generating Multimodal Empathetic Responses from Scratch |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2402.01679 |