Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
arXiv:1812.01260
Abstract
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 understanding and using conversational acts. To provide engaging conversations, Tartan blends script-like yet dynamic responses with data-based generative and retrieval models. Unique to Tartan is that our dialog manager is modeled as a dynamic Finite State Machine. To our knowledge, no other conversational agent implementation has followed this specific structure.
References in corpus (11)
- A Neural Conversational Model
- Universal Sentence Encoder
- DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset
- A Deep Reinforcement Learning Chatbot
- Conversational AI: The Science Behind the Alexa Prize
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- StarSpace: Embed All The Things!
- A Neural Network Approach to Context-Sensitive Generation of Conversational Responses
- Conversations Gone Awry: Detecting Early Signs of Conversational Failure
- Alquist: The Alexa Prize Socialbot
- Sounding Board: A User-Centric and Content-Driven Social Chatbot