Zhou Yu   俞舟

Zhou (pronounced similar to Jo)

Assistant Professor

Computer Science Department

Columbia University


Schapiro CEPSR 723

530 West 120th Street, New York, NY 10027

Email: zy2461@columbia.edu

Twitter: (I tweet more frequently than updating this webpage)

CV [pdf]


I am an Assistant Professor at the Computer Science Department, Columbia University. Before that I was an Assistant Professor at UC Davis. I received my PhD at Language Technology Institute under School of Computer Science, Carnegie Mellon University 2017, working with Prof. Alan W Black and Prof. Alexander I. Rudnicky. 2015 summer and 2016 summer, I interned with Prof. David Suendermann-Oeft at ETS San Francisco Office on cloud based multimodal dialog systems. 2014 Fall, I interned with Dan Bohus and Eric Horvitz at Microsoft Research on situated multimodal dialogue systems. I was featured on Forbes 30 under 30 in Science in 2018. My team also won the 2018 Amazon Alexa Socialbot Competition. Our work on Persuasive Dialog Systems also won ACL 2019 best paper nomination.

Prior to CMU, I received a B.S. in Computer Science and a B.A. in Linguistics under English Language Major from Zhejiang University in 2011. I worked with Prof. Xiaofei He and Prof. Deng Cai on Machine Learning and Computer Vision. I also worked with Prof. Yunhua Qu on Machine Translation.

Research Interests

I design algorithms for real-time intelligent interactive systems that coordinate with user actions that are beyond spoken languages, including non-verbal behaviors to achieve effective and natural communications. In particular, I optimize human-machine communication via studies of multimodal sensing and analysis, speech and natural language processing, machine learning and human-computer interaction. The central focus of my dissertation research is to bring together all the areas above to design, implement and deploy end-to-end real-time interactive intelligent systems that are able to plan globally considering interaction history and current user actions to achieve better user experience and task performance. Meanwhile, I enjoy collaborating with researchers with different backgrounds on interdisciplinary research in all area of science, such as health care, education and robotics.


Thanks IBM for the 2021 IBM Faculty Award

Thanks Adobe for the 2021 Adobe Faculty Award

Thanks Tencent for the 2021 Tencent Faculty Award

Please try our dialog data collection and evaluation tool kit LEGOEval code paper demo

I created the first Conversational AI course at Columbia 2021, Here is all the reading materials and corresponding slides.link

Recent talk at USC ISI, Teaching machines with natural language. video

New WeCNLP invited talk video on Builidng Dialog Systems with Less Supervsion video

Recent talk: Building Dialog Systems with Less Supervision slides

Recent talk: Gunrock, 2018 Amazon Alexa Socialbot Winner slides

Recent talk: Grounding Reinforcement Learning with Real-World Dialog Applications slides

Here is a Chinese verison of Multimodal Dialog Systems talk that targets to general public. video


I designed a Conversational AI course in Columbia, here are the reading materials and slides[link]

Our paper Persuasion For Good was nominated for ACL 2019 best paper.

We won Amazon Alexa Prize with $500,000 webpage Please refer to our system report [pdf]

I was featured on Forbes 30 under 30 in Science webpage If you want to try our chatbot, just say "Alexa Let's chat!" to any Alexa device or download the App Amazon Alexa on your phone.

If you want to do a PhD with me, please read Mor's advice Applying PhD.

Selected Publications

Weiyan Shi, Aiqi Cui, Evan Li, Ruoxi Jia and Zhou Yu, Selective Differential Privacy for Language Models, Arxiv [pdf][code]

Derek Chen and Zhou Yu, GOLD: Improving Out-of-Scope Detection in Dialogues using Data Augmentation, EMNLP 2021 [pdf][code]

Andrea Madotto, Zhaojiang Lin, Zhenpeng Zhou, Seungwhan Moon, Paul Crook, Bing Liu, Zhou Yu, Eunjoon Cho, Pascale Fung and Zhiguang Wang, Continual Learning in Task-Oriented Dialogue Systems, EMNLP 2021

Zhaojiang Lin, Bing Liu, Andrea Madotto, Seungwhan Moon, Zhenpeng Zhou, Paul Crook, Zhiguang Wang, Zhou Yu, Eunjoon Cho, Rajen Subba and Pascale Fung, Zero-Shot Dialogue State Tracking via Cross-Task Transfer, EMNLP 2021

Weiyan Shi, Yu Li, Saurav Sahay and Zhou Yu, Refine and Imitate: Reducing Repetition and Inconsistency in Persuasion Dialogues via Reinforcement Learning and Human Demonstration, EMNLP 2021 Findings

Dian Yu, Zhou Yu and Kenji Sagae, Attribute Alignment: Controlling Text Generation from Pre-trained Language Models, EMNLP 2021 Findings

Jun Zhang, Yan Yang, Chencai Chen, liang he and Zhou Yu, KERS: A Knowledge-Enhanced Framework for Recommendation Dialog Systems with Multiple Subgoals, EMNLP 2021 Findings

Kai-Hui Liang, Weiyan Shi, Yoojung Oh, Jingwen Zhang, Zhou Yu, Discovering Chatbot's Self-Disclosure's Impact on User Trust, Affinity, and Recommendation Effectiveness, arXiv [pdf]

Kai-Hui Liang, Patrick Lange, Yoo Jung Oh, Jingwen Zhang, Yoshimi Fukuoka and Zhou Yu, Evaluation of In-Person Counseling Strategies To Develop Physical Activity Chatbot for Women, SIGDIAL 2021

Satwik Kottur, Chinnadhurai Sankar, Zhou Yu and Alborz Geramifard, DialogStitch: Synthetic Deeper and Multi-Context Task-Oriented Dialogs, SIGDIAL 2021

Minh Nguyen and Zhou Yu, Improving Named Entity Recognition in Spoken Dialog Systems by Context and Speech Pattern Modeling, SIGDIAL 2021

Kun Qian, Ahmad Beirami, Zhouhan Lin, Ankita De, Alborz Geramifard, Zhou Yu and Chinnadhurai Sankar, Annotation Inconsistency and Entity Bias in MultiWOZ, SIGDIAL 2021 [pdf]

Jing Gu, Qingyang Wu, Chongruo Wu, Weiyan Shi and Zhou Yu, PRAL: A Tailored Pre-Training Model for Task-Oriented Dialog Generation, ACL 2021 [pdf][code]

Vojtěch Hudeček, Ondřej Dušek and Zhou Yu, Discovering Dialogue Slots with Weak Supervision, ACL 2021 [pdf]

Weixin Liang, Kai-Hui Liang and Zhou Yu, HERALD: An Annotation Efficient Method to Detect User Disengagement in Social Conversations, ACL 2021 [pdf][code and data][video]

David Gros, Yu Li and Zhou Yu, The R-U-A-Robot Dataset: Helping Avoid Chatbot Deception by Detecting User Questions About Human or Non-Human Identity, ACL 2021 [pdf][code and data]

Siyang Liu, Chujie Zheng, Orianna Demasi, Sahand Sabour, Yu Li, Zhou Yu, Yong Jiang and Minlie Huang, Towards Emotional Support Dialogue Systems, ACL 2021

Liang Qiu, Yuan Liang, Yizhou Zhao, Pan Lu, Baolin Peng, Zhou Yu, Ying Nian Wu and Song-Chun Zhu, SocAoG: Incremental Graph Parsing for Social Relation Inference in Dialogues, ACL 2021 [pdf] [code]

Meng Zhou, Zechen Li, Bowen Tan, Guangtao Zeng, Wenmian Yang, Xuehai He, Zeqian Ju, Subrato Chakravorty, Shu Chen, Xingyi Yang, Yichen Zhang, Qingyang Wu, Zhou Yu, Kun Xu, Eric Xing and Pengtao Xie, On the Generation of Medical Dialogs for COVID-19, ACL 2021 [pdf] [code and data]

Derek Chen, Howard Chen, Yi Yang, Alexander Lin and Zhou Yu, Action-Based Conversations Dataset:A Corpus for Building More In-Depth Task-Oriented Dialogue Systems, NAACL 2021 [pdf] [code and data]

Zhaojiang Lin, Bing Liu, Seungwhan Moon, Paul Crook, Zhenpeng Zhou, Zhiguang Wang, Zhou Yu, Andrea Madotto, Eunjoon Cho, Rajen Subba, Leveraging Slot Descriptions for Zero-Shot Cross-Domain Dialogue State Tracking, NAACL 2021 [pdf]

Mingyang Zhou, Luowei Zhou, Yu Cheng, Linjie Li, Zhou Yu, Jingjing Liu, UC2: Universal Cross-lingual Cross-modal Vision-and-Language Pretraining, CVPR 2021 [pdf] [video][code and data]

Qingyang Wu, Lei Li and Zhou Yu, TextGAIL: Generative Adversarial Imitation Learning for Text Generation, AAAI 2021 [pdf][code]

Jing Gu, Qingyang Wu and Zhou Yu, Perception Score: A Learned Metric for Open-ended Text Generation Evaluation, AAAI 2021[pdf]

Kun Qian, Wei Wei and Zhou Yu, A Student-Teacher Architecture for Dialog Domain Adaptation under the Meta-Learning Setting. AAAI 2021[pdf][code]

Jing Gu, Mostafa Mirshekari, Zhou Yu and Aaron Sisto, ChainCQG: Flow-Aware Conversational Question Generation, EACL 2021 [pdf][code]

Qingyang Wu, Yichi Zhang, Yu Li and Zhou Yu, Alternating Recurrent Dialog Model with Large-scale Pre-trained Language Models, EACL 2021 [pdf][code]

Dian Yu and Zhou Yu, MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversations, EACL 2021 [pdf][code]

David Gros, Hariharan Sezhiyan, Prem Devanbu, Zhou Yu, Code to Comment "Translation": Data, Metrics, Baselining & Evaluation, ASE 2020 [pdf]

Shirley Anugrah Hayati, Dongyeop Kang, Qingxiaoyang Zhu, Weiyan Shi and Zhou Yu, INSPIRED: Toward Sociable Recommendation Dialog Systems. EMNLP 2020 [pdf][code and data]

Liang Qiu, Yizhou Zhao, Weiyan Shi, Yuan Liang, Feng Shi, Tao Yuan, Zhou Yu, Song-Chun Zhu, Structured Attention for Unsupervised Dialogue Structure Induction, EMNLP 2020 [pdf]

Orianna Demasi, Yu Li, Zhou Yu, A Multi-Persona Chatbot for Hotline Counselor Training, Findings in EMNLP 2020, [pdf]

Weixin Liang, James Zou and Zhou Yu, ALICE: Active Learning with Contrastive Natural Language Explanations, EMNLP 2020 [pdf]

Weixin Liang, James Zou and Zhou Yu, Beyond User Self-Reported Likert Scale Ratings: A Comparison Model for Automatic Dialog Evaluation, ACL 2020 [pdf]

Silin Gao, Yichi Zhang, Zhijian Ou and Zhou Yu, Paraphrase Augmented Task-Oriented Dialog Generation, ACL 2020 [pdf]

Jiaying Hu, Yan Yang, Chencai Chen, Liang He and Zhou Yu, SAS: Dialogue State Tracking via Slot Attention and Slot Information Sharing, ACL 2020 [pdf]

Yiheng Zhou, Yulia Tsvetkov, Alan Black, and Zhou Yu, Augmenting Non-Collaborative Dialog Systems with Explicit Semantic and Strategic Dialog History, ICLR 2020, [pdf]

Weiyan Shi, Yoo Jung Oh, Xuewei Wang, Saurav Sahay, Jingwen Zhang, and Zhou Yu, Effects of Persuasive Dialogues: Testing Bot Identities and Inquiry Strategies, CHI 2020 [pdf]

Qingyang Wu, Lei Li, Hao Zhou, Ying Zeng and Zhou Yu, Importance-Aware Learning for Neural Headline Editing, AAAI 2020 [pdf]

Yu Li, Kun Qian, Weiyan Shi and Zhou Yu, End-to-End Trainable Non-Collaborative Dialog System, AAAI 2020 [pdf]

Xiyuan Zhang, Chenxi Li, Sam Davidson, Dian Yu and Zhou Yu, Filling Conversation Ellipsis for Better Social Dialog Understanding, AAAI 2020 [pdf]

Weixin Liang, Youzhi Tian, Chengcai Chen and Zhou Yu, MOSS: End-to-End Dialog System Framework with Modular Supervision, AAAI 2020 [pdf]

Yichi Zhang, Zhijian Ou and Zhou Yu, Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context, AAAI 2020 [pdf] [code]

Dian Yu & Zhou Yu, MIDAS: A Dialog Act Annotation Scheme for Open Domain Human Machine Spoken Conversations, arXiv [pdf]

Mingyang Zhou, Joshua Arnold, Zhou Yu, Building Task-Oriented Visual Dialog Systems Through Alternative Optimization Between Dialog Policy and Language Generation, EMNLP 2019 [pdf]

Weiyan Shi, Kun Qian, Xuewei Wang, Zhou Yu, How to Build User Simulators to Train RL-based Dialog Systems, EMNLP 2019 [pdf]

Sam Davidson, Dian Yu, Zhou Yu, Dependency Parsing for Spoken Dialog Systems, EMNLP 2019 [pdf]

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

Michelle Cohn, Chun-Yen Chen and Zhou Yu, A Large-Scale User Study of an Alexa Prize Chatbot: Effect of TTS Dynamism on Perceived Quality of Social Dialog, SIGDIAL 2019 [pdf]

Kun Qian & Zhou Yu, Domain Adaptive Dialog Generation via Meta Learning, ACL 2019 [pdf]

Xuewei Wang, Weiyan Shi, Richard Kim, Yoo Jung Oh, Sijia Yang, Jingwen Zhang, Zhou Yu, Persuasion for Good: Towards a Personalized Persuasive Dialogue System for Social Good, ACL 2019[pdf], [data and code] ** best paper nomination

Weiyan Shi, Tiancheng Zhao, Zhou Yu, Unsupervised Dialog Structure Learning, NAACL 2019 [pdf]

Chen et al., Gunrock: Building A Human-Like Social Bot By Leveraging Large Scale Real User Data [pdf]

Jiaao Chen, Jianshu Chen and Zhou Yu, Incorporating Structured Commonsense Knowledge in Story Completion, AAAI 2019 [pdf]

Youzhi Tian, Zhiting Hu and Zhou Yu, Structured Content Preservation for Unsupervised Text Style Transfer, arXiv 2018 [pdf]

Zijie Zhu, Xuewei Wang, Aakaash Kapoor, Tingrui Pan and Zhou Yu, EIS: A Wearable Device for Epidermal American Sign Language Recognition, IMWUT 2018 (Ubicomp 2019)[pdf]

Mingyang Zhou, Runxiang Cheng, Yong Jae Lee and Zhou Yu, A Visual Attention Grounding Neural Model for Multimodal Machine Translation, EMNLP 2018 [pdf][data]

Weiming Wen, Songwen Su and Zhou Yu, Cross-Lingual Cross-Platform Rumor Verification Pivoting on Multimedia Content, EMNLP 2018 [pdf] [code&data]

Jiaping Zhang, Tiancheng Zhao and Zhou Yu, Multimodal Hierarchical Reinforcement Learning Policy for Task-Oriented Visual Dialog, SIGDIAL 2018 [pdf]

Weiyan Shi and Zhou Yu, Sentiment Adaptive End-to-End Dialog Systems, ACL 2018 [pdf]

Ryant et al., Enhancement and Analysis of Conversational Speech: JSALT 2017, ICAASP 2018 [pdf]

Zhou Yu, Alan W Black and Alexander I. Rudnicky, Learning Conversational Systems that Interleave Task and Non-Task Content, IJCAI 2017 [pdf]

Zhou Yu, Vikram Ramanarayanan, Patrick Lange, and David Suendermann-Oeft. An open-source multimodal dialog system with real-time engagement tracking for job interview trainingapplications.In IWSDS, 2017 [pdf]

Zhou Yu, Ziyu Xu, Alan W Black and Alexander Rudnicky, Strategy and Policy Learning for Non-Task-Oriented Conversational Systems, SIGDIAL 2016. [pdf]

Zhou Yu, Leah Nicolich-Henkin, Alan W Black and Alexander Rudnicky, A Wizard-of-Oz Study on A Non-Task-Oriented Dialog Systems that Reacts to User Engagement, SIGDIAL 2016. [pdf]

Sean Andrist, Dan Bohus, Zhou Yu, Eric Horvitz, Are You Messing with Me?: Querying about the Sincerity of Interactions in the Open World. HRI 2016. [pdf]

Zhou Yu, Dan Bohus and Eric Horvitz, Incremental Coordination: Attention-Centric Speech Production in a Physically Situated Conversational Agent, SIGDIAL 2015. [pdf]

Demo Videos

TickTock: a multimodal chatbot with user engagement coordination
- below is a demo of using automatically generated conversational strategy to improve user engagement.

Direction-giving Robot: a direction-giving humanoid robot with user attention coordination
- below is a demo and some real user cases of people interacting with the robot.

HALEF: a distributed web-based multimodal dialog system with user engagement coordination
- below is a demo of a Amazon Turker interacting with our job interview training application via a web browser. It live-streams videos from usrs' local webcam to the server.