| Paper | Code | Act F1 | Slot F1 | ModelName | ReleaseDate |
|---|---|---|---|---|---|
| PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts | ✓ Link | 97.1 | 87.0 | PaCE | 2023-05-24 |
| Learning to Embed Multi-Modal Contexts for Situated Conversational Agents | 96.3 | 88.3 | BART-large | ||
| Learning to Embed Multi-Modal Contexts for Situated Conversational Agents | 95.2 | 82.0 | BART-base | ||
| Language Models are Unsupervised Multitask Learners | ✓ Link | 94.5 | 81.7 | GPT-2 | 2019-02-14 |
| Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems | ✓ Link | 93.4 | 76.7 | MTN | 2019-07-02 |