Alert button
Picture for Diyi Yang

Diyi Yang

Alert button

Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games

Dec 16, 2022
Bolin Lai, Hongxin Zhang, Miao Liu, Aryan Pariani, Fiona Ryan, Wenqi Jia, Shirley Anugrah Hayati, James M. Rehg, Diyi Yang

Figure 1 for Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
Figure 2 for Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
Figure 3 for Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
Figure 4 for Werewolf Among Us: A Multimodal Dataset for Modeling Persuasion Behaviors in Social Deduction Games
Viaarxiv icon

On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning

Dec 15, 2022
Omar Shaikh, Hongxin Zhang, William Held, Michael Bernstein, Diyi Yang

Figure 1 for On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Figure 2 for On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Figure 3 for On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Figure 4 for On Second Thought, Let's Not Think Step by Step! Bias and Toxicity in Zero-Shot Reasoning
Viaarxiv icon

DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue

Dec 15, 2022
William Held, Christopher Hidey, Fei Liu, Eric Zhu, Rahul Goel, Diyi Yang, Rushin Shah

Figure 1 for DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
Figure 2 for DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
Figure 3 for DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
Figure 4 for DAMP: Doubly Aligned Multilingual Parser for Task-Oriented Dialogue
Viaarxiv icon

Multi-VALUE: A Framework for Cross-Dialectal English NLP

Dec 15, 2022
Caleb Ziems, William Held, Jingfeng Yang, Diyi Yang

Figure 1 for Multi-VALUE: A Framework for Cross-Dialectal English NLP
Figure 2 for Multi-VALUE: A Framework for Cross-Dialectal English NLP
Figure 3 for Multi-VALUE: A Framework for Cross-Dialectal English NLP
Figure 4 for Multi-VALUE: A Framework for Cross-Dialectal English NLP
Viaarxiv icon

ConStruct-VL: Data-Free Continual Structured VL Concepts Learning

Nov 17, 2022
James Seale Smith, Paola Cascante-Bonilla, Assaf Arbelle, Donghyun Kim, Rameswar Panda, David Cox, Diyi Yang, Zsolt Kira, Rogerio Feris, Leonid Karlinsky

Figure 1 for ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
Figure 2 for ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
Figure 3 for ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
Figure 4 for ConStruct-VL: Data-Free Continual Structured VL Concepts Learning
Viaarxiv icon

Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform

Nov 09, 2022
Raj Sanjay Shah, Faye Holt, Shirley Anugrah Hayati, Aastha Agarwal, Yi-Chia Wang, Robert E. Kraut, Diyi Yang

Figure 1 for Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform
Figure 2 for Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform
Figure 3 for Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform
Figure 4 for Modeling Motivational Interviewing Strategies On An Online Peer-to-Peer Counseling Platform
Viaarxiv icon

WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain

Oct 31, 2022
Raj Sanjay Shah, Kunal Chawla, Dheeraj Eidnani, Agam Shah, Wendi Du, Sudheer Chava, Natraj Raman, Charese Smiley, Jiaao Chen, Diyi Yang

Figure 1 for WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
Figure 2 for WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
Figure 3 for WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
Figure 4 for WHEN FLUE MEETS FLANG: Benchmarks and Large Pre-trained Language Model for Financial Domain
Viaarxiv icon

Geographic Citation Gaps in NLP Research

Oct 26, 2022
Mukund Rungta, Janvijay Singh, Saif M. Mohammad, Diyi Yang

Figure 1 for Geographic Citation Gaps in NLP Research
Figure 2 for Geographic Citation Gaps in NLP Research
Figure 3 for Geographic Citation Gaps in NLP Research
Figure 4 for Geographic Citation Gaps in NLP Research
Viaarxiv icon

Robustness of Demonstration-based Learning Under Limited Data Scenario

Oct 19, 2022
Hongxin Zhang, Yanzhe Zhang, Ruiyi Zhang, Diyi Yang

Figure 1 for Robustness of Demonstration-based Learning Under Limited Data Scenario
Figure 2 for Robustness of Demonstration-based Learning Under Limited Data Scenario
Figure 3 for Robustness of Demonstration-based Learning Under Limited Data Scenario
Figure 4 for Robustness of Demonstration-based Learning Under Limited Data Scenario
Viaarxiv icon

Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers

Oct 11, 2022
William Held, Diyi Yang

Figure 1 for Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers
Figure 2 for Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers
Figure 3 for Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers
Figure 4 for Shapley Head Pruning: Identifying and Removing Interference in Multilingual Transformers
Viaarxiv icon