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 1 , 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 outof-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.

Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue

“…Engaging User Simulators and Assistant systems in synthetically generated dialogues leads to a natural reward function, and many works have used simulators in order to optimize a Reinforcement Learning policy (Schatzmann et al, 2007;Fazel-Zarandi et al, 2017;Peng et al, 2017;Su et al, 2018;Gür et al, 2018;Kreyssig et al, 2018). Such approaches are particularly used for optimizing the policy component of pipeline-based systems (Fazel-Zarandi et al, 2017), and frequently rely on the use of Natural Language Generation (NLG) templates over dialogue acts (Fazel-Zarandi et al, 2017;Shi et al, 2019;Kreyssig et al, 2018;Acharya et al, 2021). Our work instead utilizes fully lexicalized, E2E models for both the User and the Assistant models, without the need for agendas, dialogue acts, or NLG templates.…”

“…Most closely related to our work is that of and Acharya et al (2021). Similar to our approach, both use User Simulators and Schemas to generate synthetic data and add them to a training dataset.…”

“…Virtual Assistants have become ubiquitous in modern life (Acharya et al, 2021). However, building these Task Oriented Dialogue (TOD) systems is laborious, requiring significant data collection and engineering resources to add support for a novel domain.…”

“…However, building these Task Oriented Dialogue (TOD) systems is laborious, requiring significant data collection and engineering resources to add support for a novel domain. As such, methods which can generalize, learn from limited examples, and require fewer engineering resources are highly desirable (Shi et al, 2019;Acharya et al, 2021).…”

“…To this end, works have previously identified User Simulators, wherein a model is used to emulate a human user in place of a real one, as a means of addressing these problems. User Simulators have been used to evaluate (Walker et al, 1997(Walker et al, , 2000Schatzmann et al, 2005) and improve Assistant models by providing additional training data Acharya et al, 2021) and reward signals for Reinforcement Learning meth-ods (Fazel-Zarandi et al, 2017;Su et al, 2018;Shi et al, 2019). Typically, these User Simulators are either limited to enhancing existing domains (Fazel-Zarandi et al, 2017) or utilize specialized and manually engineered rules or templates for novel domains Shi et al, 2019).…”