Multi-Task Learning with Auxiliary Speaker Identification for Conversational Emotion Recognition

Jingye Li, Meishan Zhang, Donghong Ji, Yijiang Liu

2020-03-03Emotion Recognition in Conversation Speaker Identification Multi-Task Learning

Abstract

Conversational emotion recognition (CER) has attracted increasing interests in the natural language processing (NLP) community. Different from the vanilla emotion recognition, effective speaker-sensitive utterance representation is one major challenge for CER. In this paper, we exploit speaker identification (SI) as an auxiliary task to enhance the utterance representation in conversations. By this method, we can learn better speaker-aware contextual representations from the additional SI corpus. Experiments on two benchmark datasets demonstrate that the proposed architecture is highly effective for CER, obtaining new state-of-the-art results on two datasets.

Results

Task	Dataset	Metric	Value	Model
Emotion Recognition	EmoryNLP	Weighted-F1	35.92	BERT+MTL
Emotion Recognition	EmoryNLP	Weighted-F1	34.54	GloVE+MTL
Emotion Recognition	MELD	Weighted-F1	61.9	BERT+MTL
Emotion Recognition	MELD	Weighted-F1	60.69	GloVE+MTL

Related Papers

Long-Short Distance Graph Neural Networks and Improved Curriculum Learning for Emotion Recognition in Conversation2025-07-21 SGCL: Unifying Self-Supervised and Supervised Learning for Graph Recommendation2025-07-17 Robust-Multi-Task Gradient Boosting2025-07-15 Dynamic Parameter Memory: Temporary LoRA-Enhanced LLM for Long-Sequence Emotion Recognition in Conversation2025-07-11 SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation2025-07-10 Opportunistic Osteoporosis Diagnosis via Texture-Preserving Self-Supervision, Mixture of Experts and Multi-Task Integration2025-06-25 AnchorDP3: 3D Affordance Guided Sparse Diffusion Policy for Robotic Manipulation2025-06-24 An Audio-centric Multi-task Learning Framework for Streaming Ads Targeting on Spotify2025-06-23