Exploiting Unsupervised Data for Emotion Recognition in Conversations
This work addresses the data scarcity issue in ERC, a domain-specific task in conversational AI, by using unsupervised data to enhance model performance, representing an incremental advance with practical implications.
The paper tackles the problem of limited supervised data for Emotion Recognition in Conversations (ERC) by proposing a novel approach that leverages unsupervised conversation data through a Conversation Completion task and pre-training a context-dependent encoder, resulting in significant performance improvements, especially on minority emotion classes.
Emotion Recognition in Conversations (ERC) aims to predict the emotional state of speakers in conversations, which is essentially a text classification task. Unlike the sentence-level text classification problem, the available supervised data for the ERC task is limited, which potentially prevents the models from playing their maximum effect. In this paper, we propose a novel approach to leverage unsupervised conversation data, which is more accessible. Specifically, we propose the Conversation Completion (ConvCom) task, which attempts to select the correct answer from candidate answers to fill a masked utterance in a conversation. Then, we Pre-train a basic COntext- Dependent Encoder (Pre-CODE) on the ConvCom task. Finally, we fine-tune the Pre-CODE on the datasets of ERC. Experimental results demonstrate that pre-training on unsupervised data achieves significant improvement of performance on the ERC datasets, particularly on the minority emotion classes.