• #ACL2021NLP #ACL2021 Please check our group’s recent publication at the main conference of @aclmeeting. We uncovered a compositional generalization problem existing in NMT models and contributed a new dataset. Contributed by Yafu Li, Yongjing Yin, Yulong Chen, Yue Zhang.

  • Prof Yue Zhang leads the #NLP lab at Westlake University @Westlake_Uni. Our group focuses on machine learning-based natural language processing, as well as application-oriented tasks, such as web information extraction and financial market prediction. Welcome to join us!

  • #NLProc #ACL2021 G-Transformer for Document-level Machine Translation Paper:arxiv.org/abs/2105.14761 Code:github.com/baoguangsheng/ Our @aclmeeting paper at the main conference introduces locality bias to fix the failure of Transformer training on document-level MT data.

HARP-Net: Hyper-Autoencoded Reconstruction Propagation
for Scalable Neural Audio Coding

HARP-Net: Hyper-Autoencoded Reconstruction Propagation for Scalable Neural Audio Coding

HARP-Net: Hyper-Autoencoded Reconstruction Propagationfor Scalable Neural Audio Coding Abstract We propose a novel autoencoder architecture that improves the architectural scalabi……

Meta-FDMixup: Cross-Domain Few-Shot Learning 
Guided by Labeled Target Data

Meta-FDMixup: Cross-Domain Few-Shot Learning Guided by Labeled Target Data

Meta-FDMixup: Cross-Domain Few-Shot LearningGuided by Labeled Target Data Yuqian Fu1, Yanwei Fu2, Yu-Gang Jiang1#1Shanghai Key Lab of Intelligent Information Processing, School of……

Language Models as Zero-shot Visual Semantic Learner

Language Models as Zero-shot Visual Semantic Learner

Language Models as Zero-shot Visual Semantic Learner Yue JiaoUniversity of SouthamptonSouthampton, UK   Jonathon HareUniversity of SouthamptonSouthampton, UK  &emsp……

Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study

Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study

Exploiting Language Model for Efficient Linguistic Steganalysis: An Empirical Study Biao Yi, Hanzhou Wu∗, Guorui Feng and Xinpeng ZhangShanghai University, Shanghai 200444,……

Thought Flow Nets:
From Single Predictions To Trains Of Model Thought

Thought Flow Nets: From Single Predictions To Trains Of Model Thought

Thought Flow Nets:From Single Predictions To Trains Of Model Thought Hendrik Schuff 1,2  Heike Adel 1  Ngoc Thang Vu 21 Bosch Center for Artificial Intelligence, Renning……

AAVAE: Augmentation-Augmented

Variational Autoencoders

AAVAE: Augmentation-Augmented Variational Autoencoders

AAVAE: Augmentation-Augmented Variational Autoencoders William Falcon 1,2&Ananya Harsh Jha 1*&Teddy Koker 1&Kyunghyun Cho 2,31 Grid AI Labs2 New York University3 CIFAR……

Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations

Structure-Preserving Multi-Domain Stain Color Augmentation using Style-Transfer with Disentangled Representations

Structure-Preserving Multi-Domain Stain C++olor Augmentation using Style-Transfer with Disentangled Representations Sophia J. Wagner1Technical University Munich, Munich, Germany 1……

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction

H3D-Net: Few-Shot High-Fidelity 3D Head Reconstruction Eduard Ramon1,2   Gil Triginer1   Janna Escur1   Albert Pumarola3   Jaime Garcia1 &e……

Language Grounding with 3D Objects

Language Grounding with 3D Objects

Language Grounding with 3D Objects Jesse ThomasonUniversity of Southern California &Mohit Shridhar∗University of Washington/ANDYonatan BiskCarnegie Mellon University &……

Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP

Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and CLIP

Segmentation in Style: Unsupervised Semantic Image Segmentation with Stylegan and C++LIP Daniil PakhomovJohns Hopkins University   Sanchit HiraJohns Hopkins University &……