DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection

TL;DR

DialogUSR is a novel framework that splits and reformulates complex multi-intent dialogue utterances into simpler sub-queries, improving multi-intent detection in chatbots with minimal domain-specific effort.

Contribution

It introduces a new task and dataset for dialogue utterance splitting and reformulation, enabling better multi-intent detection across domains.

Findings

Proposed multiple generative models for the task.

Benchmark results highlight strengths and weaknesses of baselines.

Collected a high-quality multi-domain dataset.

Abstract

While interacting with chatbots, users may elicit multiple intents in a single dialogue utterance. Instead of training a dedicated multi-intent detection model, we propose DialogUSR, a dialogue utterance splitting and reformulation task that first splits multi-intent user query into several single-intent sub-queries and then recovers all the coreferred and omitted information in the sub-queries. DialogUSR can serve as a plug-in and domain-agnostic module that empowers the multi-intent detection for the deployed chatbots with minimal efforts. We collect a high-quality naturally occurring dataset that covers 23 domains with a multi-step crowd-souring procedure. To benchmark the proposed dataset, we propose multiple action-based generative models that involve end-to-end and two-stage training, and conduct in-depth analyses on the pros and cons of the proposed baselines.