Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent

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.

[1]  Shannon L. Spruit,et al.  Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling , 2021, ArXiv.

[2]  Pearl Pu,et al.  User Expectations of Conversational Chatbots Based on Online Reviews , 2021, Conference on Designing Interactive Systems.

[3]  Andrea Madotto,et al.  Neural Path Hunter: Reducing Hallucination in Dialogue Systems via Path Grounding , 2021, EMNLP.

[4]  Christopher D. Manning,et al.  Human-like informative conversations: Better acknowledgements using conditional mutual information , 2021, NAACL.

[5]  Mohit Bansal,et al.  I like fish, especially dolphins: Addressing Contradictions in Dialogue Modeling , 2020, ACL.

[6]  Alexander M. Rush,et al.  Pre-trained Summarization Distillation , 2020, ArXiv.

[7]  J. Weston,et al.  Recipes for Safety in Open-domain Chatbots , 2020, ArXiv.

[8]  Xiang Gao,et al.  Dialogue Response Ranking Training with Large-Scale Human Feedback Data , 2020, EMNLP.

[9]  Christopher D. Manning,et al.  Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations , 2020, ArXiv.

[10]  Eric Michael Smith,et al.  Open-Domain Conversational Agents: Current Progress, Open Problems, and Future Directions , 2020, ArXiv.

[11]  Noah A. Smith,et al.  Deep Encoder, Shallow Decoder: Reevaluating the Speed-Quality Tradeoff in Machine Translation , 2020, ArXiv.

[12]  Tom B. Brown,et al.  Language Models are Few-Shot Learners , 2020, NeurIPS.

[13]  Mary Williamson,et al.  Recipes for Building an Open-Domain Chatbot , 2020, EACL.

[14]  Mary Williamson,et al.  Can You Put it All Together: Evaluating Conversational Agents’ Ability to Blend Skills , 2020, ACL.

[15]  Quoc V. Le,et al.  Towards a Human-like Open-Domain Chatbot , 2020, ArXiv.

[16]  Peter J. Liu,et al.  PEGASUS: Pre-training with Extracted Gap-sentences for Abstractive Summarization , 2019, ICML.

[17]  Fabio Petroni,et al.  How Decoding Strategies Affect the Verifiability of Generated Text , 2019, FINDINGS.

[18]  Jianfeng Gao,et al.  DIALOGPT : Large-Scale Generative Pre-training for Conversational Response Generation , 2019, ACL.

[19]  Samuel Broscheit,et al.  Investigating Entity Knowledge in BERT with Simple Neural End-To-End Entity Linking , 2019, CoNLL.

[20]  Omer Levy,et al.  BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension , 2019, ACL.

[21]  Teven Le Scao,et al.  HuggingFace's Transformers: State-of-the-art Natural Language Processing , 2019, ArXiv.

[22]  Dian Yu,et al.  Gunrock: A Social Bot for Complex and Engaging Long Conversations , 2019, EMNLP.

[23]  Thomas Wolf,et al.  DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter , 2019, ArXiv.

[24]  Dilek Z. Hakkani-Tür,et al.  Topical-Chat: Towards Knowledge-Grounded Open-Domain Conversations , 2019, INTERSPEECH.

[25]  Lav R. Varshney,et al.  CTRL: A Conditional Transformer Language Model for Controllable Generation , 2019, ArXiv.

[26]  Verena Rieser,et al.  A Crowd-based Evaluation of Abuse Response Strategies in Conversational Agents , 2019, SIGdial.

[27]  Zhou Yu,et al.  MIDAS: A Dialog Act Annotation Scheme for Open Domain HumanMachine Spoken Conversations , 2019, EACL.

[28]  Jason Weston,et al.  Neural Text Generation with Unlikelihood Training , 2019, ICLR.

[29]  Omer Levy,et al.  RoBERTa: A Robustly Optimized BERT Pretraining Approach , 2019, ArXiv.

[30]  Meina Song,et al.  A Novel Bi-directional Interrelated Model for Joint Intent Detection and Slot Filling , 2019, ACL.

[31]  Dragomir R. Radev,et al.  Multi-News: A Large-Scale Multi-Document Summarization Dataset and Abstractive Hierarchical Model , 2019, ACL.

[32]  Yejin Choi,et al.  The Curious Case of Neural Text Degeneration , 2019, ICLR.

[33]  Marco Aurélio Gerosa,et al.  How Should My Chatbot Interact? A Survey on Social Characteristics in Human–Chatbot Interaction Design , 2019, Int. J. Hum. Comput. Interact..

[34]  Joelle Pineau,et al.  The Second Conversational Intelligence Challenge (ConvAI2) , 2019, The NeurIPS '18 Competition.

[35]  Dilek Z. Hakkani-Tür,et al.  Advancing the State of the Art in Open Domain Dialog Systems through the Alexa Prize , 2018, ArXiv.

[36]  Y-Lan Boureau,et al.  Towards Empathetic Open-domain Conversation Models: A New Benchmark and Dataset , 2018, ACL.

[37]  J. Weston,et al.  Wizard of Wikipedia: Knowledge-Powered Conversational agents , 2018, ICLR.

[38]  Stephan Schlögl,et al.  Perceptions on Authenticity in Chat Bots , 2018, Multimodal Technol. Interact..

[39]  Thomas Hofmann,et al.  End-to-End Neural Entity Linking , 2018, CoNLL.

[40]  Percy Liang,et al.  Know What You Don’t Know: Unanswerable Questions for SQuAD , 2018, ACL.

[41]  Verena Rieser,et al.  #MeToo Alexa: How Conversational Systems Respond to Sexual Harassment , 2018, EthNLP@NAACL-HLT.

[42]  Yann Dauphin,et al.  Hierarchical Neural Story Generation , 2018, ACL.

[43]  Noam Shazeer,et al.  Adafactor: Adaptive Learning Rates with Sublinear Memory Cost , 2018, ICML.

[44]  Jason Weston,et al.  Personalizing Dialogue Agents: I have a dog, do you have pets too? , 2018, ACL.

[45]  Harry Shum,et al.  From Eliza to XiaoIce: challenges and opportunities with social chatbots , 2018, Frontiers of Information Technology & Electronic Engineering.

[46]  Xiaoyu Shen,et al.  DailyDialog: A Manually Labelled Multi-turn Dialogue Dataset , 2017, IJCNLP.

[47]  Jason Weston,et al.  ParlAI: A Dialog Research Software Platform , 2017, EMNLP.

[48]  Sanjeev Arora,et al.  A Simple but Tough-to-Beat Baseline for Sentence Embeddings , 2017, ICLR.

[49]  Geoffrey E. Hinton,et al.  Distilling the Knowledge in a Neural Network , 2015, ArXiv.

[50]  Pritish Narayanan,et al.  Deep Learning with Limited Numerical Precision , 2015, ICML.

[51]  Andrea J. Vickery,et al.  The Role of “Active Listening” in Informal Helping Conversations: Impact on Perceptions of Listener Helpfulness, Sensitivity, and Supportiveness and Discloser Emotional Improvement , 2015 .

[52]  Mihai Surdeanu,et al.  The Stanford CoreNLP Natural Language Processing Toolkit , 2014, ACL.

[53]  Konstantin Beznosov,et al.  Key Challenges in Defending Against Malicious Socialbots , 2012, LEET.

[54]  Marilyn A. Walker,et al.  Endowing Virtual Characters with Expressive Conversational Skills , 2009, IVA.

[55]  Marja Kokkonen,et al.  Factors contributing to verbal self-disclosure , 2007 .

[56]  Eugene Charniak,et al.  Effective Self-Training for Parsing , 2006, NAACL.

[57]  Rada Mihalcea,et al.  TextRank: Bringing Order into Text , 2004, EMNLP.

[58]  Marilyn A. Walker,et al.  Quantitative and Qualitative Evaluation of Darpa Communicator Spoken Dialogue Systems , 2001, ACL.

[59]  A. Velthuijsen,et al.  Participation in conversations about the news. , 2001 .

[60]  Andreas Stolcke,et al.  Dialogue act modeling for automatic tagging and recognition of conversational speech , 2000, CL.

[61]  Eric Horvitz,et al.  Principles of mixed-initiative user interfaces , 1999, CHI '99.

[62]  Joseph Weizenbaum,et al.  ELIZA—a computer program for the study of natural language communication between man and machine , 1966, CACM.

[63]  Christopher D. Manning,et al.  Large-Scale Quantitative Evaluation of Dialogue Agents’ Response Strategies against Offensive Users , 2021, SIGDIAL Conferences.

[64]  Ilya Sutskever,et al.  Language Models are Unsupervised Multitask Learners , 2019 .

[65]  Ming-Wei Chang,et al.  BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding , 2019, NAACL.

[66]  R. Gunderman,et al.  Emotional intelligence. , 2011, Journal of the American College of Radiology : JACR.

[67]  Ewan Klein,et al.  Proceedings of the 38th Annual Meeting of the Association for Computational Linguistics , 2000, ACL 2000.

[68]  Elizabeth Shriberg,et al.  Switchboard SWBD-DAMSL shallow-discourse-function annotation coders manual , 1997 .

[69]  I. Altman,et al.  Social penetration: The development of interpersonal relationships , 1973 .