Emotion Recognition In Conversation On 3

Metrics

Macro F1

Micro-F1

Results

Performance results of various models on this benchmark

Model Name	Macro F1	Micro-F1	Paper Title	Repository
SKAIG-ERC	51.95	59.75	Past, Present, and Future: Conversational Emotion Recognition through Structural Modeling of Psychological Knowledge	-
CoG-BART	-	54.71	Contrast and Generation Make BART a Good Dialogue Emotion Recognizer
DAG-ERC	-	59.33	Directed Acyclic Graph Network for Conversational Emotion Recognition
CD-ERC	51.23	-	Context-Dependent Embedding Utterance Representations for Emotion Recognition in Conversations
COSMIC	51.05	58.48	COSMIC: COmmonSense knowledge for eMotion Identification in Conversations
CoMPM	53.15	60.34	CoMPM: Context Modeling with Speaker's Pre-trained Memory Tracking for Emotion Recognition in Conversation
TUCORE-GCN_RoBERTa	-	61.91	Graph Based Network with Contextualized Representations of Turns in Dialogue
KET	-	53.37	Knowledge-Enriched Transformer for Emotion Detection in Textual Conversations
TODKAT	-	58.47	Topic-Driven and Knowledge-Aware Transformer for Dialogue Emotion Detection	-
RGAT-ERC	-	54.31	Relation-aware Graph Attention Networks with Relational Position Encodings for Emotion Recognition in Conversations
KI-Net	-	57.30	Knowledge-Interactive Network with Sentiment Polarity Intensity-Aware Multi-Task Learning for Emotion Recognition in Conversations	-
Pretrained Hierarchical Transformer	-	60.14	Hierarchical Pre-training for Sequence Labelling in Spoken Dialog	-
EmotionIC	54.19	60.13	EmotionIC: emotional inertia and contagion-driven dependency modeling for emotion recognition in conversation
VHRED	-	48.4	Conversational Transfer Learning for Emotion Recognition
DialogXL	-	54.93	DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion Recognition
CESTa	-	63.12	Contextualized Emotion Recognition in Conversation as Sequence Tagging	-
TUCORE-GCN_BERT	-	58.34	Graph Based Network with Contextualized Representations of Turns in Dialogue
S+PAGE	-	64.07	S+PAGE: A Speaker and Position-Aware Graph Neural Network Model for Emotion Recognition in Conversation	-
EmoOne-RoBERTa	55.84	61.67	The Emotion is Not One-hot Encoding: Learning with Grayscale Label for Emotion Recognition in Conversation
AccumWR	-	59.22	Accumulating Word Representations in Multi-level Context Integration for ERC Task

0 of 22 row(s) selected.