# Neural Generation Meets Real People: Towards Emotionally Engaging Mixed-Initiative Conversations

arXiv: https://arxiv.org/abs/2008.12348 · HTML: https://mlsanity.com/paper/2008.12348/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 27 Aug 2020.

## Built on by (most cited first, 24 of 24)

- [Evaluating Human-Language Model Interaction](https://mlsanity.com/paper/2212.09746/) (2022)
- [Anticipating Safety Issues in E2E Conversational AI: Framework and Tooling](https://mlsanity.com/paper/2107.03451/) (2021)
- [ConvAbuse: Data, Analysis, and Benchmarks for Nuanced Abuse Detection in Conversational AI](https://mlsanity.com/paper/2109.09483/) (2021)
- [Hindsight: Posterior-guided training of retrievers for improved open-ended generation](https://mlsanity.com/paper/2110.07752/) (2021)
- [SaFeRDialogues: Taking Feedback Gracefully after Conversational Safety Failures](https://mlsanity.com/paper/2110.07518/) (2021)
- [The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity](https://mlsanity.com/paper/2106.02692/) (2021)
- [Multimodal Conversational AI: A Survey of Datasets and Approaches](https://mlsanity.com/paper/2205.06907/) (2022)
- [Alquist 4.0: Towards Social Intelligence Using Generative Models and Dialogue Personalization](https://mlsanity.com/paper/2109.07968/) (2021)
- [Robots-Dont-Cry: Understanding Falsely Anthropomorphic Utterances in Dialog Systems](https://mlsanity.com/paper/2210.12429/) (2022)
- [CASPR: A Commonsense Reasoning-based Conversational Socialbot](https://mlsanity.com/paper/2110.05387/) (2021)
- [Jurassic is (almost) All You Need: Few-Shot Meaning-to-Text Generation for Open-Domain Dialogue](https://mlsanity.com/paper/2110.08094/) (2021)
- [Proto: A Neural Cocktail for Generating Appealing Conversations](https://mlsanity.com/paper/2109.02513/) (2021)
- [Automatically Exposing Problems with Neural Dialog Models](https://mlsanity.com/paper/2109.06950/) (2021)
- [Modeling Performance in Open-Domain Dialogue with PARADISE](https://mlsanity.com/paper/2110.11164/) (2021)
- [Athena 2.0: Contextualized Dialogue Management for an Alexa Prize SocialBot](https://mlsanity.com/paper/2111.02519/) (2021)
- [Improving Bot Response Contradiction Detection via Utterance Rewriting](https://mlsanity.com/paper/2207.11862/) (2022)
- [Neural Generation Meets Real People: Building a Social, Informative Open-Domain Dialogue Agent](https://mlsanity.com/paper/2207.12021/) (2022)
- [A Systematic Evaluation of Response Selection for Open Domain Dialogue](https://mlsanity.com/paper/2208.04379/) (2022)
- [A Transformer-based Response Evaluator for Open-Domain Spoken Conversation](https://mlsanity.com/paper/2302.04424/) (2023)
- [MEDCOD: A Medically-Accurate, Emotive, Diverse, and Controllable Dialog System](https://mlsanity.com/paper/2111.09381/) (2021)
- [Safer Conversational AI as a Source of User Delight](https://mlsanity.com/paper/2304.09865/) (2023)
- [Medical Literature Mining and Retrieval in a Conversational Setting](https://mlsanity.com/paper/2108.01436/) (2021)
- [Miutsu: NTU's TaskBot for the Alexa Prize](https://mlsanity.com/paper/2205.07446/) (2022)
- [Athena 2.0: Discourse and User Modeling in Open Domain Dialogue](https://mlsanity.com/paper/2308.01887/) (2023)

## Abstract (arXiv)

We present Chirpy Cardinal, an open-domain dialogue agent, as a research platform for the 2019 Alexa Prize competition. Building an open-domain socialbot that talks to real people is challenging - such a system must meet multiple user expectations such as broad world knowledge, conversational style, and emotional connection. Our socialbot engages users on their terms - prioritizing their interests, feelings and autonomy. As a result, our socialbot provides a responsive, personalized user experience, capable of talking knowledgeably about a wide variety of topics, as well as chatting empathetically about ordinary life. Neural generation plays a key role in achieving these goals, providing the backbone for our conversational and emotional tone. At the end of the competition, Chirpy Cardinal progressed to the finals with an average rating of 3.6/5.0, a median conversation duration of 2 minutes 16 seconds, and a 90th percentile duration of over 12 minutes.