Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Fei Mi

Fei Mi

Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Dec 04, 2022
Zhexin Zhang, Jiale Cheng, Hao Sun, Jiawen Deng, Fei Mi, Yasheng Wang, Lifeng Shang, Minlie Huang

Figure 1 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Figure 2 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Figure 3 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

Figure 4 for Constructing Highly Inductive Contexts for Dialogue Safety through Controllable Reverse Generation

* Findings of EMNLP 2022

Access Paper or Ask Questions

KPT: Keyword-guided Pre-training for Grounded Dialog Generation

Dec 04, 2022
Qi Zhu, Fei Mi, Zheng Zhang, Yasheng Wang, Yitong Li, Xin Jiang, Qun Liu, Xiaoyan Zhu, Minlie Huang

Figure 1 for KPT: Keyword-guided Pre-training for Grounded Dialog Generation

Figure 2 for KPT: Keyword-guided Pre-training for Grounded Dialog Generation

Figure 3 for KPT: Keyword-guided Pre-training for Grounded Dialog Generation

Figure 4 for KPT: Keyword-guided Pre-training for Grounded Dialog Generation

* Accepted by AAAI 2023

Access Paper or Ask Questions

Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

Dec 02, 2022
Bin Sun, Yitong Li, Fei Mi, Weichao Wang, Yiwei Li, Kan Li

Figure 1 for Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

Figure 2 for Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

Figure 3 for Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

Figure 4 for Towards Diverse, Relevant and Coherent Open-Domain Dialogue Generation via Hybrid Latent Variables

* Accepted by AAAI 2023

Access Paper or Ask Questions

Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

Dec 01, 2022
Bin Sun, Shaoxiong Feng, Yiwei Li, Weichao Wang, Fei Mi, Yitong Li, Kan Li

Figure 1 for Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

Figure 2 for Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

Figure 3 for Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

Figure 4 for Modeling Complex Dialogue Mappings via Sentence Semantic Segmentation Guided Conditional Variational Auto-Encoder

* Findings of EMNLP 2022

Access Paper or Ask Questions

Continual Prompt Tuning for Dialog State Tracking

Mar 13, 2022
Qi Zhu, Bing Li, Fei Mi, Xiaoyan Zhu, Minlie Huang

Figure 1 for Continual Prompt Tuning for Dialog State Tracking

Figure 2 for Continual Prompt Tuning for Dialog State Tracking

Figure 3 for Continual Prompt Tuning for Dialog State Tracking

Figure 4 for Continual Prompt Tuning for Dialog State Tracking

* Accepted by ACL 2022, camera-ready version

Access Paper or Ask Questions

Compilable Neural Code Generation with Compiler Feedback

Mar 10, 2022
Xin Wang, Yasheng Wang, Yao Wan, Fei Mi, Yitong Li, Pingyi Zhou, Jin Liu, Hao Wu, Xin Jiang, Qun Liu

Figure 1 for Compilable Neural Code Generation with Compiler Feedback

Figure 2 for Compilable Neural Code Generation with Compiler Feedback

Figure 3 for Compilable Neural Code Generation with Compiler Feedback

Figure 4 for Compilable Neural Code Generation with Compiler Feedback

* Accepted by ACL 2022

Access Paper or Ask Questions

Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

Jan 27, 2022
Yihe Wang, Yitong Li, Yasheng Wang, Fei Mi, Pingyi Zhou, Xin Wang, Jin Liu, Qun Liu, Xin Jiang

Figure 1 for Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

Figure 2 for Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

Figure 3 for Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

Figure 4 for Pan More Gold from the Sand: Refining Open-domain Dialogue Training with Noisy Self-Retrieval Generation

* 9 pages, 3 figures

Access Paper or Ask Questions