Response Generation On Simmc2 0

BLEU

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	BLEU	Paper Title	Repository
PaCE	34.1	PaCE: Unified Multi-modal Dialogue Pre-training with Progressive and Compositional Experts
BART-base	29.4	Learning to Embed Multi-Modal Contexts for Situated Conversational Agents	-
GPT-2	19.2	Language Models are Unsupervised Multitask Learners	-
BART-large	33.1	Learning to Embed Multi-Modal Contexts for Situated Conversational Agents	-
MTN	21.7	Multimodal Transformer Networks for End-to-End Video-Grounded Dialogue Systems

0 of 5 row(s) selected.