End-to-End Learning of Flowchart Grounded Task-Oriented Dialogs

TL;DR

This paper introduces FloDial, a new dataset and neural model for end-to-end task-oriented dialogs grounded in troubleshooting flowcharts, addressing challenges like grounding, referencing manuals, and generalizing to unseen flowcharts.

Contribution

It presents a novel problem setting, a new dataset FloDial, and a retrieval-augmented neural model FloNet for flowchart-grounded task-oriented dialogs.

Findings

FloNet achieves zero-shot transfer to unseen flowcharts.

FloNet establishes a strong baseline for future research.

The dataset includes 2,738 dialogs across 12 troubleshooting flowcharts.

Abstract

We propose a novel problem within end-to-end learning of task-oriented dialogs (TOD), in which the dialog system mimics a troubleshooting agent who helps a user by diagnosing their problem (e.g., car not starting). Such dialogs are grounded in domain-specific flowcharts, which the agent is supposed to follow during the conversation. Our task exposes novel technical challenges for neural TOD, such as grounding an utterance to the flowchart without explicit annotation, referring to additional manual pages when user asks a clarification question, and ability to follow unseen flowcharts at test time. We release a dataset (FloDial) consisting of 2,738 dialogs grounded on 12 different troubleshooting flowcharts. We also design a neural model, FloNet, which uses a retrieval-augmented generation architecture to train the dialog agent. Our experiments find that FloNet can do zero-shot transfer to unseen flowcharts, and sets a strong baseline for future research.