Mem2Seq

Reported on 4 benchmarks across 2 tasks · 1 paper

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

Speech2 results

DialogueonKVRET
BLEU· 2018-04-23
12.6
best: 17.35 (TTOS)
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems arXiv:1804.08217
DialogueonKVRET
Entity F1· 2018-04-23
33.4
best: 70.07 (T5-3b(UnifiedSKG))
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems arXiv:1804.08217

Natural Language Processing2 results

Task-Oriented Dialogue SystemsonKVRET
BLEU· 2018-04-23
12.6
best: 17.35 (TTOS)
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems arXiv:1804.08217
Task-Oriented Dialogue SystemsonKVRET
Entity F1· 2018-04-23
33.4
best: 70.07 (T5-3b(UnifiedSKG))
Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems arXiv:1804.08217