Conversational Response Selection On Ubuntu 1

평가 지표

R10@1

R10@2

R10@5

평가 결과

이 벤치마크에서 각 모델의 성능 결과

				Paper Title
Dial-MAE	0.918	0.964	0.993	Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue Systems
BERT-FP+EDHNS	0.917	0.965	0.994	Efficient Dynamic Hard Negative Sampling for Dialogue Selection
Uni-Enc+BERT-FP	0.916	0.965	0.994	Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems
BERT-FP	0.911	0.962	0.994	Fine-grained Post-training for Improving Retrieval-based Dialogue Systems
Uni-Encoder	0.886	0.946	0.989	Uni-Encoder: A Fast and Accurate Response Selection Paradigm for Generation-Based Dialogue Systems
BERT-UMS+FGC	0.886	0.948	0.990	Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning
BERT-SL	0.884	0.946	0.990	Learning an Effective Context-Response Matching Model with Self-Supervised Tasks for Retrieval-based Dialogues
Poly-encoder	0.882	0.949	0.990	Poly-encoders: Transformer Architectures and Pre-training Strategies for Fast and Accurate Multi-sentence Scoring
UMS_BERT+	0.875	0.942	0.988	Do Response Selection Models Really Know What's Next? Utterance Manipulation Strategies for Multi-turn Response Selection
BERT-VFT	0.855	0.928	0.985	An Effective Domain Adaptive Post-Training Method for BERT in Response Selection
SA-BERT	0.855	0.928	0.983	Speaker-Aware BERT for Multi-Turn Response Selection in Retrieval-Based Chatbots
WDMN	0.821	0.911	0.981	Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based Dialogues
MSN	0.800	0.899	0.978	Multi-hop Selector Network for Multi-turn Response Selection in Retrieval-based Chatbots
ESIM	0.796	0.894	0.975	Sequential Attention-based Network for Noetic End-to-End Response Selection
IoI-local	0.796	0.894	0.974	One Time of Interaction May Not Be Enough: Go Deep with an Interaction-over-Interaction Network for Response Selection in Dialogues
IMN	0.794	0.889	0.974	Interactive Matching Network for Multi-Turn Response Selection in Retrieval-Based Chatbots
TripleNet	0.790	0.885	0.970	TripleNet: Triple Attention Network for Multi-Turn Response Selection in Retrieval-based Chatbots
DAM-Semi	0.785	0.883	0.974	Sampling Matters! An Empirical Study of Negative Sampling Strategies for Learning of Matching Models in Retrieval-based Dialogue Systems
DAM	0.767	0.874	0.969	Multi-Turn Response Selection for Chatbots with Deep Attention Matching Network
DAM-MG	0.753	-	-	Multi-Granularity Representations of Dialog

0 of 25 row(s) selected.

Command Palette

Conversational Response Selection On Ubuntu 1

평가 지표

평가 결과