• #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:seq2seq

MWP-BERT: A Strong Baseline for Math Word Problems

MWP-BERT: A Strong Baseline for Math Word Problems Zhenwen Liang1, Jipeng Zhang2, Jie Shao3, Xiangliang Zhang 1,∗1 King Abdullah University of Science and Technology (KAUST……

VisQA: X-raying Vision and Language Reasoning in Transformers

VisQA: X-raying Vision and Language Reasoning in Transformers Théo Jaunet*   Corentin Kervadec*   Romain Vuillemot   Grigory Antipov……

Sequence-to-Sequence Piano Transcription with Transformers

Sequence-to-Sequence Piano Transcriptionwith Transformers Abstract Automatic Music Transcription has seen significant progress in recent years by training custom deep neural netwo……

A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis

A Reinforcement Learning Environment for Mathematical Reasoning via Program Synthesis Joseph Palermo & Johnny YeCash App Labs{jpalermo, /ANDAlok SinghLawrence Berkeley Nationa……

TreeBERT: A Tree-Based Pre-Trained Model for Programming Language

TreeBERT: A Tree-Based Pre-Trained Model for Programming Language Xue JiangSchool of Information Science and EngineeringShandong Normal UniversityChina Zhuoran ZhengSchool of Comp……

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……

Increasing Faithfulness in Knowledge-Grounded Dialogue with Controllable Features

Increasing Faithfulness in Knowledge-Grounded Dialogue with C++ontrollable Features Hannah Rashkin      David Reitter      Gaurav Singh To……

The Piano Inpainting Application

The Piano Inpainting Application Gaëtan HadjeresSony Computer Science LaboratoriesParis, France&Léopold Crestel∗Sony Computer Science LaboratoriesParis, Fr……

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……

What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

What Helps Transformers Recognize C++onversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition Piotr Żelasko†‡, Raghave……