HyperAI초신경

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

한국어

HyperAI초신경

Emotion Recognition In Conversation On Cped

평가 지표

Accuracy of Sentiment

Macro-F1 of Sentiment

평가 결과

이 벤치마크에서 각 모델의 성능 결과

모델 이름	Accuracy of Sentiment	Macro-F1 of Sentiment	Paper Title	Repository
TextRNN	47.89	37.07	Recurrent Neural Network for Text Classification with Multi-Task Learning	-
FastText	48.62	30.33	Bag of Tricks for Efficient Text Classification
BERT+AVG+MLP	51.50	48.02	CPED: A Large-Scale Chinese Personalized and Emotional Dialogue Dataset for Conversational AI
DialogXL	51.24	46.96	DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
TextRCNN	49.13	37.95	Recurrent Convolutional Neural Networks for Text Classification	-
DialogueRNN	48.57	44.11	DialogueRNN: An Attentive RNN for Emotion Detection in Conversations
BERT_{utt}	48.96	45.18	BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
bcLSTM	49.65	45.40	Context-Dependent Sentiment Analysis in User-Generated Videos	-
DialogueGCN	47.69	45.12	DialogueGCN: A Graph Convolutional Neural Network for Emotion Recognition in Conversation
EmoBERTa	48.09	44.60	EmoBERTa: Speaker-Aware Emotion Recognition in Conversation with RoBERTa
TextCNN	48.90	34.37	Convolutional Neural Networks for Sentence Classification

0 of 11 row(s) selected.