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

Add to Chrome

Add to Firefox

Picture for Zhouhan Lin

Zhouhan Lin

Transkimmer: Transformer Learns to Layer-wise Skim

May 15, 2022
Yue Guan, Zhengyi Li, Jingwen Leng, Zhouhan Lin, Minyi Guo

Figure 1 for Transkimmer: Transformer Learns to Layer-wise Skim

Figure 2 for Transkimmer: Transformer Learns to Layer-wise Skim

Figure 3 for Transkimmer: Transformer Learns to Layer-wise Skim

Figure 4 for Transkimmer: Transformer Learns to Layer-wise Skim

* Published as a conference paper at ACL 2022

Access Paper or Ask Questions

RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

May 14, 2022
Jiexing Qi, Jingyao Tang, Ziwei He, Xiangpeng Wan, Chenghu Zhou, Xinbing Wang, Quanshi Zhang, Zhouhan Lin

Figure 1 for RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

Figure 2 for RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

Figure 3 for RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

Figure 4 for RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL

* 9 pages, first version

Access Paper or Ask Questions

Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

Mar 26, 2022
Xichen Pan, Peiyu Chen, Yichen Gong, Helong Zhou, Xinbing Wang, Zhouhan Lin

Figure 1 for Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

Figure 2 for Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

Figure 3 for Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

Figure 4 for Leveraging Unimodal Self-Supervised Learning for Multimodal Audio-Visual Speech Recognition

* ACL2022 Main Conference

Access Paper or Ask Questions

Block-Skim: Efficient Question Answering for Transformer

Dec 16, 2021
Yue Guan, Zhengyi Li, Jingwen Leng, Zhouhan Lin, Minyi Guo, Yuhao Zhu

Figure 1 for Block-Skim: Efficient Question Answering for Transformer

Figure 2 for Block-Skim: Efficient Question Answering for Transformer

Figure 3 for Block-Skim: Efficient Question Answering for Transformer

Figure 4 for Block-Skim: Efficient Question Answering for Transformer

* Published as a conference paper at AAAI 2022

Access Paper or Ask Questions

Incorporating External POS Tagger for Punctuation Restoration

Jun 12, 2021
Ning Shi, Wei Wang, Boxin Wang, Jinfeng Li, Xiangyu Liu, Zhouhan Lin

Figure 1 for Incorporating External POS Tagger for Punctuation Restoration

Figure 2 for Incorporating External POS Tagger for Punctuation Restoration

Figure 3 for Incorporating External POS Tagger for Punctuation Restoration

* Accepted to Interspeech 2021

Access Paper or Ask Questions

Annotation Inconsistency and Entity Bias in MultiWOZ

May 29, 2021
Kun Qian, Ahmad Beirami, Zhouhan Lin, Ankita De, Alborz Geramifard, Zhou Yu, Chinnadhurai Sankar

Figure 1 for Annotation Inconsistency and Entity Bias in MultiWOZ

Figure 2 for Annotation Inconsistency and Entity Bias in MultiWOZ

Figure 3 for Annotation Inconsistency and Entity Bias in MultiWOZ

Figure 4 for Annotation Inconsistency and Entity Bias in MultiWOZ

* Accepted by SIGDIAL 2021

Access Paper or Ask Questions

Ordered Memory

Nov 03, 2019
Yikang Shen, Shawn Tan, Arian Hosseini, Zhouhan Lin, Alessandro Sordoni, Aaron Courville

Figure 1 for Ordered Memory

Figure 2 for Ordered Memory

Figure 3 for Ordered Memory

Figure 4 for Ordered Memory

* Published in NeurIPS 2019

Access Paper or Ask Questions