paper-with-me

Dialogue Generation 벤치마크

Dialogue Generation on FusedChat

8개 결과 · ⬇ CSV · JSON

Slot Accuracy

0.972 0.9722 0.9725 0.9728 0.973 2021-09 2026-09 Classification-based model — 0.973 (2021-09-09) Two-in-one model — 0.972 (2021-09-09) Classification-based model — 0.973 (2021-09-09) Two-in-one model — 0.972 (2021-09-09) Classification-based model — 0.973 (2021-09-09) Two-in-one model — 0.972 (2021-09-09) Classification-based model — 0.973 (2021-09-09) Two-in-one model — 0.972 (2021-09-09) Classification-based model — 0.973 (2021-09-09)
RankModel Slot AccuracyJoint SAInformInform_mctSuccessSuccess_mctBLEUPPL PaperCodeYear
1 Classification-based model 0.9730.60075.190.860.974.412.1710.50 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
2 Two-in-one model 0.9720.59270.490.157.072.712.0510.49 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
3 Classification-based model 0.9730.60075.190.860.974.412.1710.50 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
4 Two-in-one model 0.9720.59270.490.157.072.712.0510.49 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
5 Classification-based model 0.9730.60075.190.860.974.412.1710.50 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
6 Two-in-one model 0.9720.59270.490.157.072.712.0510.49 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
7 Classification-based model 0.9730.60075.190.860.974.412.1710.50 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
8 Two-in-one model 0.9720.59270.490.157.072.712.0510.49 Fusing task-oriented and open-domain dialogues in conversational agents tomyoung903/fusedchat 2021
1–8 / 8 페이지당 10 20 50 100