Conversational Response Selection On Ubuntu 3
평가 지표
Accuracy
평가 결과
이 벤치마크에서 각 모델의 성능 결과
모델 이름 | Accuracy | Paper Title | Repository |
|---|---|---|---|
| MPC-BERT | 63.64 | MPC-BERT: A Pre-Trained Language Model for Multi-Party Conversation Understanding | |
| Dynamic Modeling (n=10) | 36.93 | - | - |
| SA-BERT | 60.42 | Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots | |
| DRNN | 36.93 | - | - |
| SIRNN | 40.83 | Addressee and Response Selection in Multi-Party Conversations with Speaker Interaction RNNs |
0 of 5 row(s) selected.