Sounding Board: A User-Centric and Content-Driven Social Chatbot

@inproceedings{Fang2018SoundingBA,
  title={Sounding Board: A User-Centric and Content-Driven Social Chatbot},
  author={Hao Fang and Hao Cheng and Maarten Sap and Elizabeth Clark and Ari Holtzman and Yejin Choi and Noah A. Smith and Mari Ostendorf},
  booktitle={NAACL},
  year={2018}
}
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. 
Building A User-Centric and Content-Driven Socialbot
TLDR
Observing that socialbots suffer from the issue of shallow conversations about topics associated with unstructured data, the problem of enabling extended socialbot conversations grounded on a document is studied and a graph-based document representation is proposed, together with methods for automatically constructing the graph. Expand
Tartan: A retrieval-based socialbot powered by a dynamic finite-state machine architecture
TLDR
Tartan is a non-goal-oriented socialbot focused around providing users with an engaging and fluent casual conversation that combines script-like yet dynamic responses with data-based generative and retrieval models. Expand
Gunrock: A Social Bot for Complex and Engaging Long Conversations
TLDR
Overall, it is found that users produce longer sentences to Gunrock, which are directly related to users’ engagement (e.g., ratings, number of turns), and dialog flows that interleave facts and personal opinions and stories lead to better user satisfaction. Expand
Target-Guided Open-Domain Conversation
TLDR
Quantitative and human evaluations show the proposed structured approach to imposing conversational goals on open-domain chat agents can produce meaningful and effective conversations, significantly improving over other approaches. Expand
Audrey: A Personalized Open-Domain Conversational Bot
TLDR
The University of Michigan's submission to the Alexa Prize Grand Challenge 3, Audrey, is an open-domain conversational chat-bot that aims to engage customers on these levels through interest driven conversations guided by customers' personalities and emotions. Expand
Chat or Learn: a Data-Driven Robust Question-Answering System
TLDR
A voice-based conversational agent which combines the robustness of chatbots and the utility of question answering (QA) systems, endowed with general-domain knowledge from Wikipedia articles and uses coreference resolution to detect relatedness between questions is presented. Expand
Improving Neural Conversational Models with Entropy-Based Data Filtering
TLDR
This work presents a method of filtering dialog datasets by removing generic utterances from training data using a simple entropy-based approach that does not require human supervision, and shows that training on datasets filtered this way results in better conversational quality as chatbots learn to output more diverse responses. Expand
Emotionally-Aware Chatbots: A Survey
TLDR
In this paper, a systematic review of approaches in building an emotionally-aware chatbot (EAC) is provided and it is found that in the early development, EAC exploits a simple rule-based approach while now most of EAC use neural- based approach. Expand
A Dynamic Speaker Model for Conversational Interactions
TLDR
A neural model for learning a dynamically updated speaker embedding in a conversational context is introduced and is shown to be useful for content ranking in a socialbot and dialog act prediction in human-human conversations. Expand
Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize
TLDR
Several key open-ended problems such as conversational speech recognition, open domain natural language understanding, commonsense reasoning, statistical dialog management, and dialog evaluation are addressed. Expand
...
1
2
3
4
...

References

SHOWING 1-10 OF 14 REFERENCES
Modeling Situations in Neural Chat Bots
TLDR
This paper presents neural conversational models that have general mechanisms for handling a variety of situations that affect the authors' responses, and response selection tests on massive dialogue data collected from Twitter confirmed the effectiveness of the proposed models. Expand
Conversational AI: The Science Behind the Alexa Prize
TLDR
The advances created by the university teams as well as the Alexa Prize team to achieve the common goal of solving the problem of Conversational AI are outlined. Expand
How to Make Context More Useful? An Empirical Study on Context-Aware Neural Conversational Models
TLDR
This paper conducts an empirical study to compare various models and investigate the effect of context information in dialog systems, and proposes a variant that explicitly weights context vectors by context-query relevance, outperforming the other baselines. Expand
Generating High-Quality and Informative Conversation Responses with Sequence-to-Sequence Models
TLDR
This work focuses on the single turn setting, introduces a stochastic beam-search algorithm with segment-by-segment reranking which lets us inject diversity earlier in the generation process, and proposes a practical approach, called the glimpse-model, for scaling to large datasets. Expand
A Knowledge-Grounded Neural Conversation Model
TLDR
A novel, fully data-driven, and knowledge-grounded neural conversation model aimed at producing more contentful responses that generalizes the widely-used Sequence-to-Sequence (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. Expand
Just ASK: Building an Architecture for Extensible Self-Service Spoken Language Understanding
TLDR
The design of the machine learning architecture that underlies the Alexa Skills Kit (ASK) is presented, which was the first Spoken Language Understanding Software Development Kit (SDK) for a virtual digital assistant, as far as the authors are aware. Expand
A Hierarchical Latent Variable Encoder-Decoder Model for Generating Dialogues
TLDR
A neural network-based generative architecture, with latent stochastic variables that span a variable number of time steps, that improves upon recently proposed models and that the latent variables facilitate the generation of long outputs and maintain the context. Expand
ELIZA—a computer program for the study of natural language communication between man and machine
TLDR
A discussion of some psychological issues relevant to the ELIZA approach as well as of future developments concludes the paper. Expand
The Anatomy of A.L.I.C.E.
TLDR
It is shown how to use AIML to create robot personalities like A.I.L.C.E. that pretend to be intelligent and selfaware, and some of the philosophical literature on the question of consciousness is considered, including Searle's Chinese Room, and the view that natural language understanding by a computer is impossible. Expand
An introduction to the five-factor model and its applications.
TLDR
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. Expand
...
1
2
...