Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems
Abstract
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 improvement in turn-level action signature prediction accuracy.
Cite
@article{arxiv.2104.09088,
title = {Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems},
author = {Anish Acharya and Suranjit Adhikari and Sanchit Agarwal and Vincent Auvray and Nehal Belgamwar and Arijit Biswas and Shubhra Chandra and Tagyoung Chung and Maryam Fazel-Zarandi and Raefer Gabriel and Shuyang Gao and Rahul Goel and Dilek Hakkani-Tur and Jan Jezabek and Abhay Jha and Jiun-Yu Kao and Prakash Krishnan and Peter Ku and Anuj Goyal and Chien-Wei Lin and Qing Liu and Arindam Mandal and Angeliki Metallinou and Vishal Naik and Yi Pan and Shachi Paul and Vittorio Perera and Abhishek Sethi and Minmin Shen and Nikko Strom and Eddie Wang},
journal= {arXiv preprint arXiv:2104.09088},
year = {2021}
}