Few-Shot Emotion Recognition in Conversation with Sequential Prototypical Networks

TL;DR

This paper introduces ProtoSeq, a variation of Prototypical Networks designed for few-shot emotion recognition in conversations, demonstrating effectiveness across multilingual datasets in customer service contexts.

Contribution

The paper proposes ProtoSeq, a novel sequence labeling method based on Prototypical Networks, tailored for few-shot emotion recognition in conversational settings.

Findings

ProtoSeq performs competitively with existing methods.

Effective in multilingual and low-data scenarios.

Applicable to customer service chat analysis.

Abstract

Several recent studies on dyadic human-human interactions have been done on conversations without specific business objectives. However, many companies might benefit from studies dedicated to more precise environments such as after sales services or customer satisfaction surveys. In this work, we place ourselves in the scope of a live chat customer service in which we want to detect emotions and their evolution in the conversation flow. This context leads to multiple challenges that range from exploiting restricted, small and mostly unlabeled datasets to finding and adapting methods for such context.We tackle these challenges by using Few-Shot Learning while making the hypothesis it can serve conversational emotion classification for different languages and sparse labels. We contribute by proposing a variation of Prototypical Networks for sequence labeling in conversation that we name ProtoSeq. We test this method on two datasets with different languages: daily conversations in English and customer service chat conversations in French. When applied to emotion classification in conversations, our method proved to be competitive even when compared to other ones.