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

Add to Chrome

Add to Firefox

Picture for Wenpeng Yin

Wenpeng Yin

Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Jul 24, 2022
Chang Tian, Wenpeng Yin, Marie-Francine Moens

Figure 1 for Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Figure 2 for Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Figure 3 for Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

Figure 4 for Anti-Overestimation Dialogue Policy Learning for Task-Completion Dialogue System

* NAACL Findings 2022, see https://aclanthology.org/2022.findings-naacl.43

Access Paper or Ask Questions

ConTinTin: Continual Learning from Task Instructions

Mar 18, 2022
Wenpeng Yin, Jia Li, Caiming Xiong

Figure 1 for ConTinTin: Continual Learning from Task Instructions

Figure 2 for ConTinTin: Continual Learning from Task Instructions

Figure 3 for ConTinTin: Continual Learning from Task Instructions

Figure 4 for ConTinTin: Continual Learning from Task Instructions

* ACL'2022 camera-ready

Access Paper or Ask Questions

Ultra-fine Entity Typing with Indirect Supervision from Natural Language Inference

Feb 12, 2022
Bangzheng Li, Wenpeng Yin, Muhao Chen

* Accepted to TACL. The arXiv version is a pre-MIT Press publication version

Access Paper or Ask Questions

Event Linking: Grounding Event Mentions to Wikipedia

Dec 15, 2021
Xiaodong Yu, Wenpeng Yin, Nitish Gupta, Dan Roth

Figure 1 for Event Linking: Grounding Event Mentions to Wikipedia

Figure 2 for Event Linking: Grounding Event Mentions to Wikipedia

Figure 3 for Event Linking: Grounding Event Mentions to Wikipedia

Figure 4 for Event Linking: Grounding Event Mentions to Wikipedia

* 9 pages, 9 tables, 1 figure

Access Paper or Ask Questions

Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution

Nov 20, 2021
Wenpeng Yin, Shelby Heinecke, Jia Li, Nitish Shirish Keskar, Michael Jones, Shouzhong Shi, Stanislav Georgiev, Kurt Milich, Joseph Esposito, Caiming Xiong

Figure 1 for Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution

Figure 2 for Combining Data-driven Supervision with Human-in-the-loop Feedback for Entity Resolution

* Camera-ready for Data-Centric AI Workshop at NeurIPS 2021

Access Paper or Ask Questions

DocNLI: A Large-scale Dataset for Document-level Natural Language Inference

Jun 17, 2021
Wenpeng Yin, Dragomir Radev, Caiming Xiong

Figure 1 for DocNLI: A Large-scale Dataset for Document-level Natural Language Inference

Figure 2 for DocNLI: A Large-scale Dataset for Document-level Natural Language Inference

Figure 3 for DocNLI: A Large-scale Dataset for Document-level Natural Language Inference

Figure 4 for DocNLI: A Large-scale Dataset for Document-level Natural Language Inference

* ACL'21 Findings Camera-ready

Access Paper or Ask Questions

Learning to Synthesize Data for Semantic Parsing

Apr 27, 2021
Bailin Wang, Wenpeng Yin, Xi Victoria Lin, Caiming Xiong

Figure 1 for Learning to Synthesize Data for Semantic Parsing

Figure 2 for Learning to Synthesize Data for Semantic Parsing

Figure 3 for Learning to Synthesize Data for Semantic Parsing

Figure 4 for Learning to Synthesize Data for Semantic Parsing

* NAACL 2021 short paper, fixed citation issue

Access Paper or Ask Questions

Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Apr 24, 2021
Congying Xia, Wenpeng Yin, Yihao Feng, Philip Yu

Figure 1 for Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Figure 2 for Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Figure 3 for Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

Figure 4 for Incremental Few-shot Text Classification with Multi-round New Classes: Formulation, Dataset and System

* 10 pages, accepted to NAACL 2021

Access Paper or Ask Questions