Yinhe Zheng (郑银河)

Welcome to my site!

I am currently building LLMs. I was a senior algorithm engineer at the Conversational AI Group of DAMO Academy, Alibaba. Prior to that, I finished my postdoctoral research in a joint program established on both Tsinghua University and Samsung Research. My research interests are in conversational AI, especially natural language understanding and controlled response generation.

You may also be interested in some of the Dialogue System datasets I have constructed. You can check them out in the Datasets section.

Selected Publications

* indicates equal contribution, ** indicates corresponding author.

2023

A Survey on Out-of-Distribution Detection in NLP
Transactions on Machine Learning Research
Hao Lang, Yinhe Zheng, Yixuan Li, Jian Sun, Fei Huang, Yongbin Li

PIPPA: A Partially Synthetic Conversational Dataset
Pre-print 2023 dataset
Tear Gosling, Alpin Dale, Yinhe Zheng
This paper is proudly coauthored with PygmalionAI devs.

Long-Tailed Question Answering in an Open World
ACL 2023 Main Conference (Long Paper)
Yi Dai, Hao Lang, Yinhe Zheng, Fei Huang, Yongbin Li

Domain Incremental Lifelong Learning in an Open World
ACL 2023 Fandings (Long Paper)
Yi Dai, Hao Lang, Yinhe Zheng, Bowen Yu, Fei Huang, Yongbin Li

A chatbot for mental health support: exploring the impact of Emohaa on reducing mental distress in China
Frontiers in Digital Health
Sahand Sabour, Wen Zhang, Xiyao Xiao, Yuwei Zhang, Yinhe Zheng, Jiaxin Wen, Jialu Zhao, Minlie Huang

Empathetic Response Generation via Emotion Cause Transition Graph
ICASSP 2023
Yushan Qian, Bo Wang, Ting-En Lin, Yinhe Zheng, Ying Zhu, Dongming Zhao, Yuexian Hou, Yuchuan Wu, Yongbin Li

Out-of-Domain Intent Detection Considering Multi-turn Dialogue Contexts
Pre-print 2023
Hao Lang, Yinhe Zheng, Binyuan Hui, Fei Huang, Yongbin Li

2022

Prompt Conditioned VAE: Enhancing Generative Replay for Lifelong Learning in Task-Oriented Dialogue
EMNLP 2022 Main Conference (Long Paper) [code]
Yingxiu Zhao, Yinhe Zheng**, Zhiliang Tian, Chang Gao, Jian Sun, Nevin L. Zhang

Estimating Soft Labels for Out-of-Domain Intent Detection
EMNLP 2022 Main Conference (Long Paper) (Oral)
Hao Lang, Yinhe Zheng**, Jian Sun, Fei Huang, Luo Si, Yongbin Li

CDConv: A Benchmark for Contradiction Detection in Chinese Conversations
EMNLP 2022 Main Conference (Long Paper) (Oral) [code + dataset]
Chujie Zheng, Jinfeng Zhou, Yinhe Zheng, Libiao Peng, Zhen Guo, Wenquan Wu, Zheng-Yu Niu, Hua Wu, Minlie Huang

Semi-Supervised Lifelong Language Learning
EMNLP 2022 Findings (Long Paper)
Yingxiu Zhao, Yinhe Zheng**, Bowen Yu, Zhiliang Tian, Dongkyu Lee, Jian Sun, Yongbin Li, Nevin L. Zhang

LayerConnect: Hypernetwork-Assisted Inter-Layer Connector to Enhance Parameter Efficiency
COLING 2022
Haoxiang Shi, Rongsheng Zhang, Jiaan Wang, Cen Wang, Yinhe Zheng, Tetsuya Sakai

Lifelong Learning for Question Answering with Hierarchical Prompts
Pre-print 2022
Yi Dai, Hao Lang, Yinhe Zheng, Fei Huang, Luo Si, Yongbin Li

Chatbots for Mental Health Support: Exploring the Impact of Emohaa on Reducing Mental Distress in China
Pre-print 2022
Sahand Sabour, Wen Zhang, Xiyao Xiao, Yuwei Zhang, Yinhe Zheng, Jiaxin Wen, Jialu Zhao, Minlie Huang

MMChat: Multi-Modal Chat Dataset on Social Media
LREC 2022 (Oral) [code + dataset]
Yinhe Zheng, Guanyi Chen, Xin Liu, Jian Sun

Improving Meta-learning for Low-resource Text Classification and Generation via Memory Imitation
ACL 2022 Main Conference (Long Paper)
Yingxiu Zhao, Zhiliang Tian, Huaxiu Yao, Yinhe Zheng, Dongkyu Lee, Yiping Song, Jian SUN, Nevin Zhang

Rethinking and Refining the Distinct Metric
ACL 2022 Main Conference (Short Paper)
Siyang Liu, Sahand Sabour, Yinhe Zheng, Pei Ke, Xiaoyan Zhu, Minlie Huang

GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection
AAAI 2022 (Long Paper) (Oral) [code]
Wanwei He, Yinpei Dai, Yinhe Zheng, Yuchuan Wu, Zheng Cao, Dermot Liu, Peng Jiang, Min Yang, Fei Huang, Luo Si, Jian Sun, Yongbin Li

2021

Stylized dialogue response generation using stylized unpaired texts
AAAI 2021 (Long Paper) [code]
Yinhe Zheng, Zikai Chen, Rongsheng Zhang, Shilei Huang, Xiaoxi Mao, Minlie Huang

Diversifying Dialog Generation via Adaptive Label Smoothing
ACL 2021 Main Conference (Long Paper) (Oral) [code]
Yida Wang*, Yinhe Zheng*, Yong Jiang, Minlie Huang

Transferable Persona-Grounded Dialogues via Grounded Minimal Edits
EMNLP 2021 Main Conference (Long Paper)
Chen Henry Wu, Yinhe Zheng, Xiaoxi Mao, Minlie Huang

Unsupervised Domain Adaptation with Adapter
NeurIPS 2021 ENLSP Workshop
Rongsheng Zhang*, Yinhe Zheng*, Xiaoxi Mao, Minlie Huang

EVA: An Open-Domain Chinese Dialogue System with Large-Scale Generative Pre-Training
Pre-print 2021
Hao Zhou, Pei Ke, Zheng Zhang, Yuxian Gu, Yinhe Zheng, Chujie Zheng, Yida Wang, Chen Henry Wu, Hao Sun, Xiaocong Yang, Bosi Wen, Xiaoyan Zhu, Minlie Huang, Jie Tang

Semantic-Enhanced Explainable Finetuning for Open-Domain Dialogues
Pre-print 2021
Chen Henry Wu, Yinhe Zheng, Yida Wang, Zhenyu Yang, Minlie Huang

2020

A pre-training based personalized dialogue generation model with persona-sparse data
AAAI 2020 (Long Paper)
Yinhe Zheng, Rongsheng Zhang, Minlie Huang, Xiaoxi Mao

Dialogue distillation: Open-domain dialogue augmentation using unpaired data
EMNLP 2020 Main Conference (Long Paper)
Rongsheng Zhang*, Yinhe Zheng*, Jianzhi Shao, Xiaoxi Mao, Yadong Xi, Minlie Huang

A large-scale chinese short-text conversation dataset
NLPCC 2020 (Best Student Paper) [code + dataset]
Yida Wang, Pei Ke, Yinhe Zheng, Kaili Huang, Yong Jiang, Xiaoyan Zhu, Minlie Huang

Out-of-domain detection for natural language understanding in dialog systems
IEEE/ACM Transactions on Audio, Speech, and Language Processing [code]
Yinhe Zheng, Guanyi Chen, Minlie Huang </span>

Listener’s Social Identity Matters in Personalised Response Generation
INLG 2020
Guanyi Chen, Yinhe Zheng, Yupei Du

2019

Personalized dialogue generation with diversified traits
Pre-print
Yinhe Zheng, Guanyi Chen, Minlie Huang, Song Liu, Xuan Zhu

Persona-aware Dialogue Generation with Enriched Profile
NIPS2019 ConvAI Workshop (Best Paper Nominee)
Yinhe Zheng, Guanyi Chen, Minlie Huang, Song Liu, Xuan Zhu