Sounding Board: A User-Centric and Content-Driven Social Chatbot
Hao Fang,Hao Cheng,Maarten Sap,Elizabeth Clark,Ari Holtzman,Yejin Choi,Noah A. Smith,Mari Ostendorf +7 more
- pp 96-100
Reads0
Chats0
TLDR
Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize, consists of several components including spoken language processing, dialogue management, language generation, and content management with emphasis on user-centric and content-driven design as discussed by the authors.Abstract:
We present Sounding Board, a social chatbot that won the 2017 Amazon Alexa Prize. The system architecture consists of several components including spoken language processing, dialogue management, language generation, and content management, with emphasis on user-centric and content-driven design. We also share insights gained from large-scale online logs based on 160,000 conversations with real-world users.read more
Citations
More filters
Journal ArticleDOI
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
TL;DR: XiaoIce as mentioned in this paper is the most popular social chatbot in the world and is designed as an artifical intelligence companion with an emotional con to the chatbot.
Journal ArticleDOI
Challenges in Building Intelligent Open-domain Dialog Systems
TL;DR: This article reviews the recent work on neural approaches that are devoted to addressing three challenges in developing intelligent open-domain dialog systems: semantics, consistency, and interactiveness.
Posted Content
The Design and Implementation of XiaoIce, an Empathetic Social Chatbot
TL;DR: This article describes the development of Microsoft XiaoIce, the most popular social chatbot in the world, and shows how XiaoIce dynamically recognizes human feelings and states, understands user intent, and responds to user needs throughout long conversations.
Proceedings ArticleDOI
Grounded Conversation Generation as Guided Traverses in Commonsense Knowledge Graphs
TL;DR: ConceptFlow as mentioned in this paper presents a new conversation generation model, ConceptFlow, which leverages commonsense knowledge graphs to explicitly model conversation flows and represents the potential conversation flow as traverses in the concept space along commonsense relations.
Proceedings ArticleDOI
Target-Guided Open-Domain Conversation
TL;DR: This article proposed a structured approach that introduces coarse-grained keywords to control the intended content of system responses, and then attain smooth conversation transition through turn-level supervised learning, and drive the conversation towards the target with discourse-level constraints.
References
More filters
Journal ArticleDOI
An introduction to the five-factor model and its applications.
Robert R. McCrae,Oliver P. John +1 more
TL;DR: It is argued that the five-factor model of personality should prove useful both for individual assessment and for the elucidation of a number of topics of interest to personality psychologists.
Journal ArticleDOI
ELIZA — a computer program for the study of natural language communication between man and machine
TL;DR: A discussion of some psychological issues relevant to the ELIZA approach as well as of future developments concludes the paper.
Journal ArticleDOI
The mini-IPIP scales: tiny-yet-effective measures of the Big Five factors of personality.
TL;DR: The Mini-IPIP scales showed a comparable pattern of convergent, discriminant, and criterion-related validity with other Big Five measures, indicating that it is a psychometrically acceptable and practically useful short measure of the Big Five factors of personality.
Proceedings Article
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
Iulian Vlad Serban,Alessandro Sordoni,Ryan Lowe,Laurent Charlin,Joelle Pineau,Aaron Courville,Yoshua Bengio +6 more
TL;DR: The authors proposed a neural network-based generative architecture with stochastic latent variables that span a variable number of time steps to generate meaningful, long and diverse responses and maintain dialogue state.
Proceedings Article
A Knowledge-Grounded Neural Conversation Model
Marjan Ghazvininejad,Chris Brockett,Ming-Wei Chang,Bill Dolan,Jianfeng Gao,Wen-tau Yih,Michel Galley +6 more
TL;DR: The authors generalize the Seq2Seq approach by conditioning responses on both conversation history and external "facts", allowing the model to be versatile and applicable in an open-domain setting.