Label effcient semi-supervised conversational intent classifcation

Abstract

To provide a convenient shopping experience and to answer user queries at scale, conversational platforms are essential for e-commerce. The user queries can be pre-purchase questions, such as product speci-fcations and delivery time related, or post-purchase queries, such as exchange and return. A chatbot should be able to understand and answer a variety of such queries to help users with relevant information. One of the important modules in the chat-bot is automated intent identifcation, i.e., understanding the user's intention from the query text. Due to non-English speaking users interacting with the chatbot, we often get a signifcant percentage of code mix queries and queries with grammatical errors, which makes the problem more challenging. This paper proposes a simple yet competent Semi-Supervised Learning (SSL) approach for label-effcient intent classifcation. We use a small labeled corpus and relatively larger unlabeled query data to train a transformer model. For training the model with labeled data, we explore supervised MixUp data augmentation. To train with unlabeled data, we explore label consistency with dropout noise. We experiment with different pre-trained transformer architectures, such as BERT and sentence-BERT. Experimental results demonstrate that the proposed approach signifcantly improves over the supervised baseline, even with a limited labeled set. A variant of the model is currently deployed in production.