InstructERC: Reforming Emotion Recognition in Conversation with a Retrieval Multi-task LLMs Framework

21 Sep 2023  ·  Shanglin Lei, Guanting Dong, XiaoPing Wang, Keheng Wang, Sirui Wang ·

The field of emotion recognition of conversation (ERC) has been focusing on separating sentence feature encoding and context modeling, lacking exploration in generative paradigms based on unified designs. In this study, we propose a novel approach, \textbf{InstructERC}, to reformulate the ERC task from a discriminative framework to a generative framework based on Large Language Models (LLMs). InstructERC makes three significant contributions: (1) it introduces a simple yet effective retrieval template module, which helps the model explicitly integrate multi-granularity dialogue supervision information. (2) We introduce two additional emotion alignment tasks, namely speaker identification and emotion prediction tasks, to implicitly model the dialogue role relationships and future emotional tendencies in conversations. (3) Pioneeringly, we unify emotion labels across benchmarks through the feeling wheel to fit real application scenarios. InstructERC still perform impressively on this unified dataset. Our LLM-based plugin framework significantly outperforms all previous models and achieves comprehensive SOTA on three commonly used ERC datasets. Extensive analysis of parameter-efficient and data-scaling experiments provides empirical guidance for applying it in practical scenarios. Our code and aligned unified dataset (UIME) can be found in the Github link.\footnote{You can find the offical realization in the Github link: https://github.com/LIN-SHANG/InstructERC}

PDF Abstract
Task Dataset Model Metric Name Metric Value Global Rank Result Benchmark
Emotion Recognition in Conversation EmoryNLP InstructERC Weighted-F1 41.39 # 2
Emotion Recognition in Conversation IEMOCAP InstructERC Weighted-F1 71.39 # 6
Accuracy 71.68 # 4
Emotion Recognition in Conversation MELD InstructERC Weighted-F1 69.15 # 2

Methods


No methods listed for this paper. Add relevant methods here