EMNLP Findings2023
Efficient Cross-Task Prompt Tuning for Few-Shot Conversational Emotion Recognition
Yige Xu, Zhiwei Zeng, Zhiqi Shen
Abstract
Emotion Recognition in Conversation (ERC) has been widely studied due to its importance in developing emotion-aware empathetic machines. The rise of pre-trained language models (PLMs) has further pushed the limit of ERC performance. However, most recent works on ERC using PLMs are heavily datadriven and require fine-tuning the entire PLMs. To improve both sample and computational efficiency, we propose a derivative-free optimization method called Cross-Task Prompt Tuning (CTPT) for few-shot conversational emotion recognition. Unlike existing methods that learn independent knowledge from individual tasks, CTPT leverages sharable crosstask knowledge by exploiting external knowledge from other source tasks to improve learning performance under the few-shot setting. Moreover, CTPT only needs to optimize a vector under the low intrinsic dimensionality without gradient, which is highly training-efficient compared with existing approaches. Experiments on five different contextual conversation datasets demonstrate that our CTPT method has superior results on both few-shot scenarios and zero-shot transfers.
Ask Lune
Know this paper in minutes, not an afternoon.
Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.
4 top-tier papers have cited it since. Know what they found before your reviewers do.
Lune can draw on
the full paper · the top-tier papers that cite it · related work
Free to start. No credit card required.
Lineage
- SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer cites Language Models are Few-Shot Learners
- SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs cites Language Models are Few-Shot Learners
- Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in Conversation cites COSMIC: COmmonSense knowledge for eMotion Identification in Conversations
- PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt Tuning cites SPoT: Better Frozen Model Adaptation through Soft Prompt Transfer
- Zero-Shot Video Question Answering via Frozen Bidirectional Language Models cites Language Models are Few-Shot Learners
Cited by top-tier papers4
- PT-MoE: An Efficient Finetuning Framework for Integrating Mixture-of-Experts into Prompt TuningZongqian Li, Yixuan Su, Nigel CollierNeurIPS 2025 · 7 citations
- Emotion Transfer with Enhanced Prototype for Unseen Emotion Recognition in ConversationKun Peng, Cong Cao, Hao Peng, Guanlin Wu et al.EMNLP 2025 · 1 citation
- EmoBench: Evaluating the Emotional Intelligence of Large Language ModelsSahand Sabour, Siyang Liu, Zheyuan Zhang, June M. Liu et al.ACL 2024
- SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMsYige Xu, Xu Guo, Zhiwei Zeng, Chunyan MiaoACL 2025
Builds on15
- Language Models are Few-Shot LearnersTom B. Brown, Benjamin Mann, Nick Ryder, Melanie Subbiah et al.NeurIPS 2020 · 64,255 citations
- COSMIC: COmmonSense knowledge for eMotion Identification in ConversationsDeepanway Ghosal, Navonil Majumder, Alexander F. Gelbukh, Rada Mihalcea et al.EMNLP Findings 2020 · 390 citations
- SPoT: Better Frozen Model Adaptation through Soft Prompt TransferTu Vu, Brian Lester, Noah Constant, Rami Al-Rfou' et al.ACL 2022 · 332 citations
- Zero-Shot Video Question Answering via Frozen Bidirectional Language ModelsAntoine Yang, Antoine Miech, Josef Sivic, Ivan Laptev et al.NeurIPS 2022 · 305 citations
- DialogXL: All-in-One XLNet for Multi-Party Conversation Emotion RecognitionWeizhou Shen, Junqing Chen, Xiaojun Quan, Zhixian XieAAAI 2021 · 251 citations
Related papers
- ADPL: Adversarial Prompt-based Domain Adaptation for Dialogue Summarization with Knowledge DisentanglementLulu Zhao, Fujia Zheng, Weihao Zeng, Keqing He et al.SIGIR 2022 · 6 citations
- PPT: Pre-trained Prompt Tuning for Few-shot LearningYuxian Gu, Xu Han, Zhiyuan Liu, Minlie HuangACL 2022
- Multimodal Prompt Transformer with Hybrid Contrastive Learning for Emotion Recognition in ConversationShihao Zou, Xianying Huang, Xudong ShenACM MM 2023 · 24 citations
- Multilingual Relation Classification via Efficient and Effective PromptingYuxuan Chen, David Harbecke, Leonhard HennigEMNLP 2022 · 13 citations
- TransPrompt: Towards an Automatic Transferable Prompting Framework for Few-shot Text ClassificationChengyu Wang, Jianing Wang, Minghui Qiu, Jun Huang et al.EMNLP 2021 · 39 citations
