Alert button
Picture for Dilek Hakkani-Tur

Dilek Hakkani-Tur

Alert button

Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks

Jun 01, 2022
Yifan Chen, Tianning Xu, Dilek Hakkani-Tur, Di Jin, Yun Yang, Ruoqing Zhu

Figure 1 for Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
Figure 2 for Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
Figure 3 for Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
Figure 4 for Calibrate and Debias Layer-wise Sampling for Graph Convolutional Networks
Viaarxiv icon

Understanding How People Rate Their Conversations

Jun 01, 2022
Alexandros Papangelis, Nicole Chartier, Pankaj Rajan, Julia Hirschberg, Dilek Hakkani-Tur

Figure 1 for Understanding How People Rate Their Conversations
Figure 2 for Understanding How People Rate Their Conversations
Figure 3 for Understanding How People Rate Their Conversations
Figure 4 for Understanding How People Rate Their Conversations
Viaarxiv icon

On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets

May 18, 2022
Hyounghun Kim, Aishwarya Padmakumar, Di Jin, Mohit Bansal, Dilek Hakkani-Tur

Figure 1 for On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
Figure 2 for On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
Figure 3 for On the Limits of Evaluating Embodied Agent Model Generalization Using Validation Sets
Viaarxiv icon

Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention

May 07, 2022
Yifan Chen, Devamanyu Hazarika, Mahdi Namazifar, Yang Liu, Di Jin, Dilek Hakkani-Tur

Figure 1 for Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Figure 2 for Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Figure 3 for Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Figure 4 for Empowering parameter-efficient transfer learning by recognizing the kernel structure in self-attention
Viaarxiv icon

What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation

Mar 25, 2022
Sarik Ghazarian, Behnam Hedayatnia, Alexandros Papangelis, Yang Liu, Dilek Hakkani-Tur

Figure 1 for What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation
Figure 2 for What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation
Figure 3 for What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation
Figure 4 for What is wrong with you?: Leveraging User Sentiment for Automatic Dialog Evaluation
Viaarxiv icon

Towards Textual Out-of-Domain Detection without In-Domain Labels

Mar 22, 2022
Di Jin, Shuyang Gao, Seokhwan Kim, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Towards Textual Out-of-Domain Detection without In-Domain Labels
Figure 2 for Towards Textual Out-of-Domain Detection without In-Domain Labels
Figure 3 for Towards Textual Out-of-Domain Detection without In-Domain Labels
Figure 4 for Towards Textual Out-of-Domain Detection without In-Domain Labels
Viaarxiv icon

Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges

Mar 18, 2022
Shikib Mehri, Jinho Choi, Luis Fernando D'Haro, Jan Deriu, Maxine Eskenazi, Milica Gasic, Kallirroi Georgila, Dilek Hakkani-Tur, Zekang Li, Verena Rieser, Samira Shaikh, David Traum, Yi-Ting Yeh, Zhou Yu, Yizhe Zhang, Chen Zhang

Figure 1 for Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges
Figure 2 for Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges
Viaarxiv icon

Multi-Sentence Knowledge Selection in Open-Domain Dialogue

Mar 01, 2022
Mihail Eric, Nicole Chartier, Behnam Hedayatnia, Karthik Gopalakrishnan, Pankaj Rajan, Yang Liu, Dilek Hakkani-Tur

Figure 1 for Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Figure 2 for Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Figure 3 for Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Figure 4 for Multi-Sentence Knowledge Selection in Open-Domain Dialogue
Viaarxiv icon

Analyzing the Limits of Self-Supervision in Handling Bias in Language

Dec 16, 2021
Lisa Bauer, Karthik Gopalakrishnan, Spandana Gella, Yang Liu, Mohit Bansal, Dilek Hakkani-Tur

Figure 1 for Analyzing the Limits of Self-Supervision in Handling Bias in Language
Figure 2 for Analyzing the Limits of Self-Supervision in Handling Bias in Language
Figure 3 for Analyzing the Limits of Self-Supervision in Handling Bias in Language
Figure 4 for Analyzing the Limits of Self-Supervision in Handling Bias in Language
Viaarxiv icon

Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences

Dec 10, 2021
Yifan Chen, Qi Zeng, Dilek Hakkani-Tur, Di Jin, Heng Ji, Yun Yang

Figure 1 for Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Figure 2 for Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Figure 3 for Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Figure 4 for Sketching as a Tool for Understanding and Accelerating Self-attention for Long Sequences
Viaarxiv icon