Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent
Authors:
- Ethan A. ChiECEthan A. Chi
- Ashwin ParanjapeAPAshwin Paranjape
- Abigail SeeASAbigail See
- Caleb ChiamCCCaleb Chiam
- Amelia HardyAHAmelia Hardy
- Chetanya RastogiCRChetanya Rastogi
- Haojun LiHLHaojun Li
- Alexander IyaborAIAlexander Iyabor
- Yutong HeYHYutong He
Preprint
Abstract
We present Chirpy Cardinal, an open-domain social chatbot. Aiming to be both informative and conversational, our bot chats with users in an authentic, emotionally intelligent way. By integrating controlled neural generation with scaffolded, hand-written dialogue, we let both the user and bot take turns driving the conversation, producing an engaging and socially fluent experience. Deployed in the fourth iteration of the Alexa Prize Socialbot Grand Challenge, Chirpy Cardinal handled thousands of conversations per day, placing second out of nine bots with an average user rating of 3.58/5.Keywords
All Related Versions
This publication has 16 references indexed in Scilit:
- MIDAS: A Dialog Act Annotation Scheme for Open Domain HumanMachine Spoken Conversations2021
- Recipes for Building an Open-Domain Chatbot2021
- Dialogue Response Ranking Training with Large-Scale Human Feedback Data2020
- How Decoding Strategies Affect the Verifiability of Generated Text2020
- Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills2020
- From Eliza to XiaoIce: challenges and opportunities with social chatbotsFrontiers of Information Technology & Electronic Engineering, 2018
- ParlAI: A Dialog Research Software Platform2017
- Factors contributing to verbal self-disclosureNordic Psychology, 2007
- Dialogue Act Modeling for Automatic Tagging and Recognition of Conversational SpeechComputational Linguistics, 2000
- ELIZA—a computer program for the study of natural language communication between man and machineCommunications of the ACM, 1966