• #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:multi-task learning

QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading Comprehension

QA Dataset Explosion: A Taxonomy of NLP Resources for Question Answering and Reading C++omprehension Anna Rogers1234-5678-9012University of Copenhagen (Denmark)RIKEN (Japan), ……

Persistent Reinforcement Learning via Subgoal Curricula

Persistent Reinforcement Learning via Subgoal C++urricula Archit Sharma†‡, Abhishek Gupta#‡, Sergey Levine#‡, Karol Hausman‡†, Chelsea Fi……

Offline Meta-Reinforcement Learning with Advantage Weighting

Offline Meta-Reinforcement Learning with Advantage Weighting Eric Mitchell1, Rafael Rafailov1, Xue Bin Peng2, Sergey Levine2, Chelsea Finn11 Stanford University, 2 UC Berkeley A……

Recurrent Parameter Generators

Recurrent Parameter Generators Jiayun Wang  1Yubei Chen∗ 2Stella X. Yu1Brian Cheung4Yann LeCun2,31 UC Berkeley / ICSI  2 Facebook AI Research3 New Yor……

Know Deeper: Knowledge-Conversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation

Know Deeper: Knowledge-C++onversation Cyclic Utilization Mechanism for Open-domain Dialogue Generation Yajing Sun1,2, Yue Hu1,21, Luxi Xing1,2, Jing Yu1,2, Yuqiang Xie1,2, Xiangp……

CatVRNN: Generating Category Texts via Multi-task Learning

C++atVRNN: Generating Category Texts via Multi-task Learning Pengsen ChengCorresponding Author:School of Cyber Science and Engineering, Sichuan UniversityJiayong LiuSchool of Cybe……

Spatial and Temporal Networks for Facial Expression Recognition in the Wild Videos

Spatial and Temporal Networks for Facial Expression Recognitionin the Wild Videos Shuyi Mao1,∗, Xinqi Fan2,∗, Xiaojiang Peng1,∗,†1Shenzhen Technology U……

From Show to Tell: A Survey on Image Captioning

From Show to Tell:A Survey on Image Captioning Matteo Stefanini, Marcella Cornia, Lorenzo Baraldi, Silvia Cascianelli,Giuseppe Fiameni, and Rita ……

Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills

Turning Tables: Generating Examples from Semi-structured Tables for Endowing Language Models with Reasoning Skills Ori Yoran1 /Thanks Work done while working at the Allen Institu……

Ensemble-based Semi-supervised Learning to Improve Noisy Soiling Annotations in Autonomous Driving

Ensemble-based Semi-supervised Learning to ImproveNoisy Soiling Annotations in Autonomous Driving Michal Uřičář1, Ganesh Sistu2, Lucie Yahiaoui2 and Senthil……