Research map / Large language models / Language, safety and interpretability
Emotional Chatting Machine: Emotional Conversation Generation with Internal and External Memory
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Add emotion category embedding, internal memory, and external memory | Seq2Seq · ESTC test | emotion accuracy: 0.179 -> 0.773 | Helped |
| Add emotion category embedding, internal memory, and external memory | Seq2Seq · ESTC test | perplexity: 68.0 -> 65.9 | Helped |
| Add internal memory and external memory to emotion category embedding | Emb · ESTC test | emotion accuracy: 0.724 -> 0.773 | Helped |
| Add internal memory and external memory to emotion category embedding | Emb · Manual evaluation, overall | content score: 1.256 -> 1.299 | Helped |
| Add internal memory and external memory to emotion category embedding | Emb · Manual evaluation, overall | emotion score: 0.363 -> 0.424 | Helped |
| Add emotion category embedding (ablation) | ECM · ESTC test | emotion accuracy: 0.753 -> 0.773 | Helped |
| Add emotion category embedding (ablation) | ECM · ESTC test | perplexity: 66.1 -> 65.9 | Helped |
| Add internal memory (ablation) | ECM · ESTC test | emotion accuracy: 0.749 -> 0.773 | Helped |
| Add internal memory (ablation) | ECM · ESTC test | perplexity: 66.7 -> 65.9 | Helped |
| Add external memory (ablation) | ECM · ESTC test | emotion accuracy: 0.731 -> 0.773 | Helped |
| Add external memory (ablation) | ECM · ESTC test | perplexity: 61.8 -> 65.9 | Hurt |
| Use ECM instead of Emb | Emotional response generation · Angry responses | manual content score: 1.035 -> 0.98 | Hurt |
Closest papers by meaning
- Infusing Multi-Source Knowledge with Heterogeneous Graph Neural Network for Emotional Conversation Generation (AAAI 2021 · similarity 0.90)
- Emotion Rendering for Conversational Speech Synthesis with Heterogeneous Graph-Based Context Modeling (AAAI 2024 · similarity 0.87)
- MemoryBank: Enhancing Large Language Models with Long-Term Memory (AAAI 2024 · similarity 0.86)
- SD-Eval: A Benchmark Dataset for Spoken Dialogue Understanding Beyond Words (NeurIPS 2024 · similarity 0.85)
- The Good, The Bad, and Why: Unveiling Emotions in Generative AI (ICML 2024 · similarity 0.85)
- SocialSim: Towards Socialized Simulation of Emotional Support Conversation (AAAI 2025 · similarity 0.84)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.