Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Personalized And Emotional Conversation On

Métriques

Average Embedding

BLEU

Distinct-1

Distinct-2

Greedy Embedding

PPL

bertscore

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	Average Embedding	BLEU	Distinct-1	Distinct-2	Greedy Embedding	PPL	bertscore	Paper Title	Repository
{emo+da}-GPT w/o emo	0.5564	0.1252	0.0451	0.2746	0.4964	22.84	0.5666	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
GPT-{per+emo}	0.5617	0.1403	0.0602	0.3388	0.5026	17.70	0.5719	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
{emo+da}-GPT	0.5552	0.1304	0.0476	0.2785	0.4962	21.60	0.5674	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
GPT-{per}	0.5606	0.1372	0.0592	0.3363	0.5009	18.08	0.5715	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
GPT-{da}	0.5610	0.1372	0.0605	0.3389	0.5017	17.72	0.5703	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
GPT	0.5509	0.1171	0.0482	0.2738	0.4922	20.07	0.5629	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
{emo+da}-GPT w/o da	0.5556	0.1272	0.0473	0.2790	0.4962	22.09	0.5669	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
GPT-{per+emo+da}	0.5608	0.1382	0.0601	0.3404	05012	17.80	0.5722	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
GPT-{emo}	0.5588	0.1342	0.0614	0.3430	0.4996	17.48	0.5709	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI

0 of 9 row(s) selected.