TESS: A Multi-intent Parser for Conversational Multi-Agent Systems with Decentralized Natural Language Understanding Models
Authors:
Preprint
Abstract
Chatbots have become one of the main pathways for the delivery of business automation tools. Multi-agent systems offer a framework for designing chatbots at scale, making it easier to support complex conversations that span across multiple domains as well as enabling developers to maintain and expand their capabilities incrementally over time. However, multi-agent systems complicate the natural language understanding (NLU) of user intents, especially when they rely on decentralized NLU models: some utterances (termed single intent) may invoke a single agent while others (termed multi-intent) may explicitly invoke multiple agents. Without correctly parsing multi-intent inputs, decentralized NLU approaches will not achieve high prediction accuracy. In this paper, we propose an efficient parsing and orchestration pipeline algorithm to service multi-intent utterances from the user in the context of a multi-agent system. Our proposed approach achieved comparable performance to competitive deep learning models on three different datasets while being up to 48 times faster.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- Training Naturalized Semantic Parsers with Very Little Data2022
- A Conversational Digital Assistant for Intelligent Process Automation2020
- Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey2020
- Robotic Process Automation: Systematic Literature Review2019
- Artificial Intelligence Tool Penetration in Business: Adoption, Challenges and Fears2019
- MultiWOZ - A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling2018
- Zero-shot User Intent Detection via Capsule Neural Networks2018
- Exploiting shared information for multi-intent natural language sentence classification2013
- Deep belief nets for natural language call-routing2011
- Optimizing SVMs for complex call classification2003