Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2026
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866912951337746432 |
|---|---|
| author | Tanaka, Yoshiki Uehara, Ryuichi Inoue, Koji Inaba, Michimasa |
| author_facet | Tanaka, Yoshiki Uehara, Ryuichi Inoue, Koji Inaba, Michimasa |
| contents | Emotion Recognition in Conversation (ERC) is critical for enabling natural human-machine interactions. However, existing methods predominantly employ categorical or dimensional emotion annotations, which often fail to adequately represent complex, subtle, or culturally specific emotional nuances. To overcome this limitation, we propose a novel task named Emotion Transcription in Conversation (ETC). This task focuses on generating natural language descriptions that accurately reflect speakers' emotional states within conversational contexts. To address the ETC, we constructed a Japanese dataset comprising text-based dialogues annotated with participants' self-reported emotional states, described in natural language. The dataset also includes emotion category labels for each transcription, enabling quantitative analysis and its application to ERC. We benchmarked baseline models, finding that while fine-tuning on our dataset enhances model performance, current models still struggle to infer implicit emotional states. The ETC task will encourage further research into more expressive emotion understanding in dialogue. The dataset is publicly available at https://github.com/UEC-InabaLab/ETCDataset. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_07138 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language Tanaka, Yoshiki Uehara, Ryuichi Inoue, Koji Inaba, Michimasa Computation and Language Artificial Intelligence Emotion Recognition in Conversation (ERC) is critical for enabling natural human-machine interactions. However, existing methods predominantly employ categorical or dimensional emotion annotations, which often fail to adequately represent complex, subtle, or culturally specific emotional nuances. To overcome this limitation, we propose a novel task named Emotion Transcription in Conversation (ETC). This task focuses on generating natural language descriptions that accurately reflect speakers' emotional states within conversational contexts. To address the ETC, we constructed a Japanese dataset comprising text-based dialogues annotated with participants' self-reported emotional states, described in natural language. The dataset also includes emotion category labels for each transcription, enabling quantitative analysis and its application to ERC. We benchmarked baseline models, finding that while fine-tuning on our dataset enhances model performance, current models still struggle to infer implicit emotional states. The ETC task will encourage further research into more expressive emotion understanding in dialogue. The dataset is publicly available at https://github.com/UEC-InabaLab/ETCDataset. |
| title | Emotion Transcription in Conversation: A Benchmark for Capturing Subtle and Complex Emotional States through Natural Language |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2603.07138 |