SOTAVerified

Conversational Response Selection

Conversational response selection refers to the task of identifying the most relevant response to a given input sentence from a collection of sentences.

Papers

Showing 110 of 46 papers

TitleStatusHype
Efficient Dynamic Hard Negative Sampling for Dialogue SelectionCode0
P5: Plug-and-Play Persona Prompting for Personalized Response SelectionCode0
Knowledge-aware response selection with semantics underlying multi-turn open-domain conversationsCode0
Dial-MAE: ConTextual Masked Auto-Encoder for Retrieval-based Dialogue SystemsCode0
Learning Dialogue Representations from Consecutive UtterancesCode1
One Agent To Rule Them All: Towards Multi-agent Conversational AICode0
Two-Level Supervised Contrastive Learning for Response Selection in Multi-Turn Dialogue0
Small Changes Make Big Differences: Improving Multi-turn Response Selection in Dialogue Systems via Fine-Grained Contrastive Learning0
Exploring Dense Retrieval for Dialogue Response SelectionCode1
Response Ranking with Multi-types of Deep Interactive Representations in Retrieval-based DialoguesCode0
Show:102550
← PrevPage 1 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1SEMSOL(W/o utterances)MAP0.65Unverified
2Uni-Enc+BERT-FPMAP0.65Unverified
3BERT-FPMAP0.64Unverified
4SEMSOLMAP0.64Unverified
5SA-BERT+HCLMAP0.64Unverified
6UMS_BERT+MAP0.63Unverified
7Uni-EncoderMAP0.62Unverified
8SA-BERTMAP0.62Unverified
9Poly-encoderMAP0.61Unverified
10BERTMAP0.59Unverified