Deploying a Retrieval based Response Model for Task Oriented Dialogues
This addresses the need for scalable and adaptable conversational models in business applications, but it is incremental as it builds on existing retrieval-based and neural ranking methods.
The paper tackled the problem of developing a task-oriented dialogue system for industry settings by proposing a 3-step procedure involving template creation, neural ranking, and two-stage learning, resulting in deployment with live customers and offline experiments.
Task-oriented dialogue systems in industry settings need to have high conversational capability, be easily adaptable to changing situations and conform to business constraints. This paper describes a 3-step procedure to develop a conversational model that satisfies these criteria and can efficiently scale to rank a large set of response candidates. First, we provide a simple algorithm to semi-automatically create a high-coverage template set from historic conversations without any annotation. Second, we propose a neural architecture that encodes the dialogue context and applicable business constraints as profile features for ranking the next turn. Third, we describe a two-stage learning strategy with self-supervised training, followed by supervised fine-tuning on limited data collected through a human-in-the-loop platform. Finally, we describe offline experiments and present results of deploying our model with human-in-the-loop to converse with live customers online.