Research map / Label-efficient and robust learning / Recognition and long-tail
Addressee and Response Selection in Multi-Party Conversations With Speaker Interaction RNNs
Rui Zhang, Honglak Lee, Lazaros Polymenakos, Dragomir Radev
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 |
|---|---|---|---|
| use role-sensitive speaker updates and joint addressee-response selection | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15 | ADR-RES accuracy: 54.88 -> 67.30 | Improved |
| use role-sensitive speaker updates and joint addressee-response selection | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15 | ADR-RES accuracy: 27.19 -> 35.76 | Improved |
| use role-sensitive speaker updates and joint addressee-response selection | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15 | ADR accuracy: 68.54 -> 80.47 | Improved |
| use role-sensitive speaker updates and joint addressee-response selection | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15 | RES accuracy: 36.93 -> 40.83 | Improved |
| add role-specific parameters for sender, addressee, and observer update units (ablation) | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15 | ADR-RES accuracy: 59.47 -> 67.30 | Improved |
| add role-specific parameters for sender, addressee, and observer update units (ablation) | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15 | ADR-RES accuracy: 28.45 -> 35.76 | Improved |
| jointly select the addressee and response rather than selecting them separately (ablation) | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=2, T=15 | ADR-RES accuracy: 63.40 -> 67.30 | Improved |
| jointly select the addressee and response rather than selecting them separately (ablation) | SI-RNN · Ubuntu Multiparty Conversation Corpus, test, RES-CAND=10, T=15 | ADR-RES accuracy: 32.53 -> 35.76 | Improved |
Closest papers by meaning
- Friends-MMC: A Dataset for Multi-modal Multi-party Conversation Understanding (AAAI 2025 · similarity 0.85)
- Aligning Spoken Dialogue Models from User Interactions (ICML 2025 · similarity 0.85)
- MultiTalk: Scaling Full-Duplex Speech Models to Long, Multi-Party, Bilingual Conversation (NeurIPS 2026 · similarity 0.84)
- NTPP: Generative Speech Language Modeling for Dual-Channel Spoken Dialogue via Next-Token-Pair Prediction (ICML 2025 · similarity 0.84)
- Uni-MIS: United Multiple Intent Spoken Language Understanding via Multi-View Intent-Slot Interaction (AAAI 2024 · similarity 0.83)
- An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems (ICML 2024 · similarity 0.83)
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.
