Abstract
Intelligent personal assistants (IPAs) such as Amazon Alexa, Google Assistant and Apple Siri extend their built-in capabilities by supporting voice apps developed by third-party developers. Sometimes the smart assistant is not able to successfully respond to user voice commands (aka utterances). There are many reasons including automatic speech recognition (ASR) error, natural language understanding (NLU) error, routing utterances to an irrelevant voice app or simply that the user is asking for a capability that is not supported yet. The failure to handle a voice command leads to customer frustration. In this paper, we introduce a fallback skill recommendation system to suggest a voice app to a customer for an unhandled voice command. One of the prominent challenges of developing a skill recommender system for IPAs is partial observation. To solve the partial observation problem, we propose collaborative data relabeling (CDR) method. In addition, CDR also improves the diversity of the recommended skills. We evaluate the proposed method both offline and online. The offline evaluation results show that the proposed system outperforms the baselines. The online A/B testing results show significant gain of customer experience metrics.
Highlights
1 Introduction found such as music, video, book, recipe, etc
We propose a skill recommender system for Intelligent personal assistants (IPAs) to handle unclaimed utterances by exploiting the ever-increasing 3P voice apps
collaborative data relabeling (CDR) mitigates the partial observation problem by trying to answer a counterfactual question, "what if we present another skill to the user?"
Summary
To reduce customer friction and recover the conversation, we propose a skill recommender system which proactively suggests 3P skills to users for unhandled requests, even if the users are not aware of the skills Intelligent personal assistants such as Alexa, Siri, posed of two components: a shortlister, and a and Google Assistant have been becoming more reranker. A large amount of are passed to the reranker that ranks the skill canthird-party (3P) voice apps (aka skills) have been didates by using skill specific information and the developed These voice apps extend IPAs built-in utterance. The supported 3P skills can number up to that are not handled by the existing system Traditional recommender systems such as video recommendation recommend a ranked list of items to a user. Online experimental results show significant gains of user experience metrics such as higher volume of acceptances, lower friction rates, etc
Sign-in/Register to view highlights & summary 
Published Version (
Free)
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call