• #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.

标签:ethical

The social dilemma in AI development and why we have to solve it

The social dilemma in AI development and why we have to solve it Inga StrümkeInga Strümke Department of Engineering Cybernetics, NTNU, Trondheim, NorwayDepartment o……

Audio2Head: Audio-driven One-shot Talking-head Generation with Natural Head Motion

Audio2Head: Audio-driven One-shot Talking-head Generationwith Natural Head Motion Suzhen Wang1  Lincheng Li1  Yu Ding1Corresponding author.  Changji……

Deep Learning on a Data Diet: Finding Important Examples Early in Training

Deep Learning on a Data Diet:Finding Important Examples Early in Training Mansheej PaulStanford University&Surya GanguliStanford University; Facebook AI Research∧Gintare K……

Learning Algebraic Recombination for Compositional Generalization

Learning Algebraic Recombination for C++ompositional Generalization Chenyao Liu1  Shengnan An2∗  Zeqi Lin3  Qian Liu4∗  Bei Chen3  Jian-Gua……

NeurIPS 2021 Competition proposal: The MineRL Basalt Competition on Learning from Human Feedback

NeurIPS 2021 C++ompetition proposal: The MineRL Basalt Competition on Learning from Human Feedback Rohin Shah           Cody Wild……

Deep Extrapolation for Attribute-Enhanced Generation

Deep Extrapolation forAttribute-Enhanced Generation Alvin Chan* Salesforce Research, NTU &Ali Madani* Salesforce Research &Ben Krause Salesforce Research &Nikhil Naik ……

Ethics Sheets for AI Tasks

Ethics Sheets for AI Tasks Saif M. MohammadNational Research Council Canada Abstract Several high-profile events, such as the use of biased recidivism systems and mass testing……

Using AntiPatterns to avoid MLOps Mistakes

Using AntiPatterns to avoid MLOps Mistakes Nikil Muralidhar1, Sathappan Muthiah1, Patrick Butler1,Manish Jain2, Yu Yu2, Katy Burne2, Weipeng Li2, David Jones2Prakash Arunachalam2,……

AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction

AutoLAW: Augmented Legal Reasoning through Legal Precedent Prediction Robert Zev MahariMIT Media LabHarvard Law School Abstract This paper demonstrate how NLP can be used to ad……

Towards the Right Kind of Fairness in AIA guide on the different metrics. And the tool “Fairness Compass” to choose the best option for your project.

Towards the Right Kind of Fairness in AI A guide on the different metrics. And the tool “Fairness Compass” to choose the best option for your project. Boris RufAXA G……