论文标题
Dialogusr：复杂的对话说法分裂和重新制定多次意图检测
DialogUSR: Complex Dialogue Utterance Splitting and Reformulation for Multiple Intent Detection
论文作者
论文摘要
在与聊天机器人进行互动时，用户可能会在单个对话话语中引起多种意图。我们提出了Dialogusr，而不是训练专用的多键检测模型，而是对对话说法分裂和重新制定任务，该任务首先将多Indignent用户查询分配到几个单意大利子征询中，然后在子征服中恢复所有核心和省略的信息。 Dialogusr可以用作插件和域名模块，该模块能够以最小的努力为部署的聊天机器人赋予多大检测。我们收集了一个自然存在的高质量数据集，该数据集涵盖了23个域，并具有多步群体程序。为了基准拟议的数据集，我们提出了涉及端到端和两阶段训练的多个基于动作的生成模型，并对拟议基准的利弊进行了深入的分析。
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.
