Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems

by   Anish Acharya, et al.

Traditional goal-oriented dialogue systems rely on various components such as natural language understanding, dialogue state tracking, policy learning and response generation. Training each component requires annotations which are hard to obtain for every new domain, limiting scalability of such systems. Similarly, rule-based dialogue systems require extensive writing and maintenance of rules and do not scale either. End-to-End dialogue systems, on the other hand, do not require module-specific annotations but need a large amount of data for training. To overcome these problems, in this demo, we present Alexa Conversations, a new approach for building goal-oriented dialogue systems that is scalable, extensible as well as data efficient. The components of this system are trained in a data-driven manner, but instead of collecting annotated conversations for training, we generate them using a novel dialogue simulator based on a few seed dialogues and specifications of APIs and entities provided by the developer. Our approach provides out-of-the-box support for natural conversational phenomena like entity sharing across turns or users changing their mind during conversation without requiring developers to provide any such dialogue flows. We exemplify our approach using a simple pizza ordering task and showcase its value in reducing the developer burden for creating a robust experience. Finally, we evaluate our system using a typical movie ticket booking task and show that the dialogue simulator is an essential component of the system that leads to over 50% improvement in turn-level action signature prediction accuracy.


page 1

page 2

page 3

page 4


DLGNet-Task: An End-to-end Neural Network Framework for Modeling Multi-turn Multi-domain Task-Oriented Dialogue

Task oriented dialogue (TOD) requires the complex interleaving of a numb...

Integrating Pre-trained Model into Rule-based Dialogue Management

Rule-based dialogue management is still the most popular solution for in...

Data-Driven Dialogue Systems for Social Agents

In order to build dialogue systems to tackle the ambitious task of holdi...

PolyResponse: A Rank-based Approach to Task-Oriented Dialogue with Application in Restaurant Search and Booking

We present PolyResponse, a conversational search engine that supports ta...

A Corpus of Controlled Opinionated and Knowledgeable Movie Discussions for Training Neural Conversation Models

Fully data driven Chatbots for non-goal oriented dialogues are known to ...

Edina: Building an Open Domain Socialbot with Self-dialogues

We present Edina, the University of Edinburgh's social bot for the Amazo...

Slugbot: An Application of a Novel and Scalable Open Domain Socialbot Framework

In this paper we introduce a novel, open domain socialbot for the Amazon...

Please sign up or login with your details

Forgot password? Click here to reset