HiDialog

Reported on 3 benchmarks across 2 tasks · 1 paper · 2 SOTA

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Natural Language Processing2 results

Relation ExtractiononDialogRE
F1 (v2)· 2023-04-29
77.1
SOTA
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention arXiv:2305.00262
Relation ExtractiononDialogRE
F1c (v2)· 2023-04-29
68.2
best: 69.8 (DiaRE-D2G)
SOTA
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention arXiv:2305.00262

Audio1 result

Emotion RecognitiononMELD
Weighted-F1· 2023-04-29
66.96
best: 69.9 (ELR-GNN)
Hierarchical Dialogue Understanding with Special Tokens and Turn-level Attention arXiv:2305.00262