HyperAI초신경

홈 뉴스 최신 연구 논문 튜토리얼 데이터셋 백과사전 SOTA LLM 모델 GPU 랭킹 컨퍼런스

한국어

HyperAI초신경

Task Oriented Dialogue Systems On Kvret

평가 지표

BLEU

Entity F1

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	BLEU	Entity F1	Paper Title	Repository
TTOS	17.35	55.38	Amalgamating Knowledge from Two Teachers for Task-oriented Dialogue System with Adversarial Training
Mem2Seq	12.6	33.4	Mem2Seq: Effectively Incorporating Knowledge Bases into End-to-End Task-Oriented Dialog Systems
COMET	17.3	63.6	Contextualize Knowledge Bases with Transformer for End-to-end Task-Oriented Dialogue Systems	-
GLMP	14.79	59.97	Global-to-local Memory Pointer Networks for Task-Oriented Dialogue
DSR	12.7	51.9	Sequence-to-Sequence Learning for Task-oriented Dialogue with Dialogue State Representation	-
T5-3b(UnifiedSKG)	-	70.07	UnifiedSKG: Unifying and Multi-Tasking Structured Knowledge Grounding with Text-to-Text Language Models
KB-retriever	13.9	53.7	Entity-Consistent End-to-end Task-Oriented Dialogue System with KB Retriever
KV Retrieval Net	13.2	48.0	Key-Value Retrieval Networks for Task-Oriented Dialogue
DF-Net	15.2	62.5	Dynamic Fusion Network for Multi-Domain End-to-end Task-Oriented Dialog
THPN	12.8	37.8	A Template-guided Hybrid Pointer Network for Knowledge-based Task-oriented Dialogue Systems

0 of 10 row(s) selected.