Towards Scalable Multi-Domain Conversational Agents: The Schema-Guided Dialogue Dataset
Abhinav Rastogi, Xiaoxue Zang, Srinivas Sunkara, Raghav Gupta, Pranav Khaitan Google Research, Mountain View, California, USA {abhirast, xiaoxuez, srinivasksun, raghavgupta,
Abstract
Virtual assistants such as Google Assistant, Alexa and Siri provide a conversational interface to a large number of services and APIs spanning multiple domains. Such systems need to support an ever-increasing number of services with possibly overlapping functionality. Furthermore, some of these services have little to no training data available. Existing public datasets for task-oriented dialogue do not sufficiently capture these challenges since they cover few domains and assume a single static ontology per domain. In this work, we introduce the the Schema-Guided Dialogue (SGD) dataset, containing over 16k multi-domain conversations spanning 16 domains. Our dataset exceeds the existing task-oriented dialogue corpora in scale, while also highlighting the challenges associated with building large-scale virtual assistants. It provides a challenging testbed for a number of tasks including language understanding, slot filling, dialogue state tracking and response generation. Along the same lines, we present a schema-guided paradigm for task-oriented dialogue, in which predictions are made over a dynamic set of intents and slots, provided as input, using their natural language descripti
中文速览
虚拟助手要同时支持海量、不断新增的服务，现有多领域对话数据集规模太小、每个领域只有单一固定接口，根本无法覆盖这一挑战。为此，研究者发布了"模式引导对话"数据集（Schema-Guided Dialogue，SGD），包含逾1.6万段跨16个领域、45项服务的多轮对话，并提出一种"模式引导范式"——把每个服务的意图（intent）和槽位（slot）的自然语言描述直接作为模型输入，让单一对话系统无需额外训练数据就能处理全新服务。基于该范式，他们构建了一个结合BERT预训练语言模型的对话状态追踪（dialogue state tracking）模型，在对未见过的API实现零样本泛化的同时，在标准数据集上也保持了有竞争力的性能。这项工作既为学术界提供了目前最大的公开任务型对话基准，也为工业界打造可扩展、易集成新服务的对话系统提供了切实可行的技术路径。
原文 arXiv:1909.05855;中英对照 + 大白话阅读 https://aha.fim.ai/paper/1909.05855v2