Building chatbots from large scale domain-specific knowledge bases: challenges and opportunities

TL;DR

This paper discusses the challenges of building chatbots with large domain-specific knowledge bases, proposing a scalable framework that improves entity recognition accuracy and understanding of user utterances in specialized domains.

Contribution

It introduces a novel scalable framework for extracting and learning domain-specific entities, outperforming existing methods in large-scale knowledge integration.

Findings

30% more accurate entity recognition compared to popular off-the-shelf frameworks

Better scalability with large volumes of domain-specific entities

Enhanced understanding of user utterances in equipment-related complaints

Abstract

Popular conversational agents frameworks such as Alexa Skills Kit (ASK) and Google Actions (gActions) offer unprecedented opportunities for facilitating the development and deployment of voice-enabled AI solutions in various verticals. Nevertheless, understanding user utterances with high accuracy remains a challenging task with these frameworks. Particularly, when building chatbots with large volume of domain-specific entities. In this paper, we describe the challenges and lessons learned from building a large scale virtual assistant for understanding and responding to equipment-related complaints. In the process, we describe an alternative scalable framework for: 1) extracting the knowledge about equipment components and their associated problem entities from short texts, and 2) learning to identify such entities in user utterances. We show through evaluation on a real dataset that the proposed framework, compared to off-the-shelf popular ones, scales better with large volume of entities being up to 30% more accurate, and is more effective in understanding user utterances with domain-specific entities.