Gunrock 2.0: A User Adaptive Social Conversational System
arXiv:2011.08906
Abstract
Gunrock 2.0 is built on top of Gunrock with an emphasis on user adaptation. Gunrock 2.0 combines various neural natural language understanding modules, including named entity detection, linking, and dialog act prediction, to improve user understanding. Its dialog management is a hierarchical model that handles various topics, such as movies, music, and sports. The system-level dialog manager can handle question detection, acknowledgment, error handling, and additional functions, making downstream modules much easier to design and implement. The dialog manager also adapts its topic selection to accommodate different users' profile information, such as inferred gender and personality. The generation model is a mix of templates and neural generation models. Gunrock 2.0 is able to achieve an average rating of 3.73 at its latest build from May 29th to June 4th.
Published in 3rd Proceedings of Alexa Prize (Alexa Prize 2020)
References in corpus (19)
- A Neural Conversational Model
- Wizard of Wikipedia: Knowledge-Powered Conversational agents
- Training Deep Neural Networks on Noisy Labels with Bootstrapping
- Deep Reinforcement Learning for Dialogue Generation
- Chameleons in imagined conversations: A new approach to understanding coordination of linguistic style in dialogs
- Towards a Human-like Open-Domain Chatbot
- A Diversity-Promoting Objective Function for Neural Conversation Models
- Personalizing Dialogue Agents: I have a dog, do you have pets too?
- Learning Discourse-level Diversity for Neural Dialog Models using Conditional Variational Autoencoders
- DialoGPT: Large-Scale Generative Pre-training for Conversational Response Generation
- From Eliza to XiaoIce: Challenges and Opportunities with Social Chatbots
- Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
- Deep Active Learning for Named Entity Recognition
- Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models
- Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good
- MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversations
- Alquist: The Alexa Prize Socialbot
- Sounding Board: A User-Centric and Content-Driven Social Chatbot
- Detecting Offensive Content in Open-domain Conversations using Two Stage Semi-supervision