Figure 2 - uploaded by Ankit Shah
Content may be subject to copyright.
Download
View publication
System Architecture Diagram

System Architecture Diagram

Source publication
Figure 2: System Architecture Diagram
Figure 4: A regression analysis of sentiment score against scaled...
Figure 5: Percent of FSM turns in a conversation vs the average scaled...
Figure 6: Average scaled conversation rating vs date. The ratings have...
Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
Preprint
Full-text available
  • Dec 2018
This paper describes the Tartan conversational agent built for the 2018 Alexa Prize Competition. Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation. Tartan's key features include an emphasis on structured conversation based on flexible finite-state models and an approach focused on...
Cite
Download full-text

Contexts in source publication

Context 1
... teams, such as Sounding Board, used their response output manager to control prosody [Fang et al., 2018]. Figure 2 shows the design of the Tartan socialbot. It makes use of the infrastructure provided by the Amazon Alexa Prize team (COBOT), which was based on their analysis of system architectures developed during the first competition. ...
Context 2
... teams, such as Sounding Board, used their response output manager to control prosody [Fang et al., 2018]. Figure 2 shows the design of the Tartan socialbot. It makes use of the infrastructure provided by the Amazon Alexa Prize team (COBOT), which was based on their analysis of system architectures developed during the first competition. ...