The Technology Behind Personal Digital Assistants: An overview of the system architecture and key components

By Ruhi Sarikaya. 2017

194 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Information Systems and Management

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

In Information Systems and Management

Citations in the corpus

Out-of-Domain Detection for Natural Language Understanding in Dialog Systems (2019, methodology): “Recently, various deep neural network (DNN) based NLU models have been proposed and applied in real-world applications (Kim et al., 2018; Sarikaya, 2017; Yoo et al., 2018).”
From Eliza to XiaoIce: challenges and opportunities with social chatbots (2018, background): “IPAs provide reactive and proactive assistance to users to accomplish a variety of tasks (Sarikaya 2017).”
Detecting Absurd Conversations from Intelligent Assistant Logs by Exploiting User Feedback Utterances (2018, background): “Quality metrics can be divided into component metrics and end-to-end metrics [21].”
Towards Designing Cooperative and Social Conversational Agents for Customer Service (2017, methodology): “CS research has focused on improving the technical capabilities of CAs by developing better algorithms (e.g., Griol et al. 2008) or new architectures (Sarikaya 2017).”
Efficient Large-Scale Domain Classification with Personalized Attention (2018, background): “Many IPDAs have recently emerged in industry including Amazon Alexa, Google Assistant, Apple Siri, and Microsoft Cor-tana (Sarikaya, 2017).”
How perceptions of intelligence and anthropomorphism affect adoption of personal intelligent agents (2020, background): “Intelligent agents exist in different forms of digital agents such as personal digital agents, conversational agents, embodied conversational agents, chatbots, etc. (see Appendix 1, Table 3; see Sarikaya, 2017; Maedche et al., 2019; McTear, 2016; von Wolff et al., 2019; Nunamaker et al., 2011).”
Probabilistic Extension of Precision, Recall, and F1 Score for More Thorough Evaluation of Classification Models (2020, background): “In the Natural Language Processing (NLP) industry, new challenges have risen in the past few years in terms of performance evaluation, due to the complexity and scalable design of modern NLP systems such as those powering Google Assistant, Amazon Alexa, or Apple’s Siri (Sarikaya, 2017).”
Joint Learning of Domain Classification and Out-of-Domain Detection with Dynamic Class Weighting for Satisficing False Acceptance Rates (2018, background): “Since recent spoken dialog systems such as Amazon Alexa, Google Assistant, Microsoft Cortana, and Apple Siri deal with a wide variety of scenarios [2, 3], correct domain classification of a user’s utterance into one of the supported domains or out-of-domain (OOD) is becoming more complex and importa”