# TESS: A Multi-intent Parser for Conversational Multi-Agent Systems with Decentralized Natural Language Understanding Models

arXiv: https://arxiv.org/abs/2312.11828 · HTML: https://mlsanity.com/paper/2312.11828/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 16 of its 50 references that are in the map.
- First posted on arXiv 19 Dec 2023.

## Builds on (most cited first, 16 of 16)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [A Stack-Propagation Framework with Token-Level Intent Detection for Spoken Language Understanding](https://mlsanity.com/paper/1909.02188/) (2019)
- [Rasa: Open Source Language Understanding and Dialogue Management](https://mlsanity.com/paper/1712.05181/) (2017)
- [Zero-shot User Intent Detection via Capsule Neural Networks](https://mlsanity.com/paper/1809.00385/) (2018)
- [Recent Neural Methods on Slot Filling and Intent Classification for Task-Oriented Dialogue Systems: A Survey](https://mlsanity.com/paper/2011.00564/) (2020)
- [DIET: Lightweight Language Understanding for Dialogue Systems](https://mlsanity.com/paper/2004.09936/) (2020)
- [CM-Net: A Novel Collaborative Memory Network for Spoken Language Understanding](https://mlsanity.com/paper/1909.06937/) (2019)
- [Structure-aware Fine-tuning of Sequence-to-sequence Transformers for Transition-based AMR Parsing](https://mlsanity.com/paper/2110.15534/) (2021)
- [Improving Semantic Parsing for Task Oriented Dialog](https://mlsanity.com/paper/1902.06000/) (2019)
- [Planning for Goal-Oriented Dialogue Systems](https://mlsanity.com/paper/1910.08137/) (2019)
- [One Agent To Rule Them All: Towards Multi-agent Conversational AI](https://mlsanity.com/paper/2203.07665/) (2022)
- [A Conversational Digital Assistant for Intelligent Process Automation](https://mlsanity.com/paper/2007.13256/) (2020)
- [D3BA: A Tool for Optimizing Business Processes Using Non-Deterministic Planning](https://mlsanity.com/paper/2001.02619/) (2020)
- [Explainable Composition of Aggregated Assistants](https://mlsanity.com/paper/2011.10707/) (2020)

## Abstract (arXiv)

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.