Transformers

SHAPE: Shifted Absolute Position Embedding for Transformers EMNLP 2021 “Sharks are not the threat humans are”: Argument Component Segmentation in School Student Essays EACL 2021 Shifted Chunk Transformer for Spatio-Temporal Representational Learning NeurIPS 2021 SideControl: Controlled Open-domain Dialogue Generation via Additive Side Networks EMNLP 2021 SIGMORPHON 2021 Shared Task on Morphological Reinflection: Generalization Across Languages ACL 2021 Similar Language Translation for Catalan, Portuguese and Spanish Using Marian NMT EMNLP 2021 SimpleNER Sentence Simplification System for GEM 2021 ACL 2021 Single Pair Cross-Modality Super Resolution CVPR 2021 SketchGen: Generating Constrained CAD Sketches NeurIPS 2021 Skyformer: Remodel Self-Attention with Gaussian Kernel and Nystr\"om Method NeurIPS 2021 Small Model and In-Domain Data Are All You Need EMNLP 2021 SnowflakeNet: Point Cloud Completion by Snowflake Point Deconvolution With Skip-Transformer ICCV 2021 SOAT: A Scene- and Object-Aware Transformer for Vision-and-Language Navigation NeurIPS 2021 SOE-Net: A Self-Attention and Orientation Encoding Network for Point Cloud Based Place Recognition CVPR 2021 SOFT: Softmax-free Transformer with Linear Complexity NeurIPS 2021 SOLQ: Segmenting Objects by Learning Queries NeurIPS 2021 Solving Machine Learning Problems ACML 2021 SOTR: Segmenting Objects With Transformers ICCV 2021 Space Efficient Context Encoding for Non-Task-Oriented Dialogue Generation with Graph Attention Transformer ACL 2021 Space-Time Crop & Attend: Improving Cross-Modal Video Representation Learning ICCV 2021 Space-time Mixing Attention for Video Transformer NeurIPS 2021 Span Pointer Networks for Non-Autoregressive Task-Oriented Semantic Parsing EMNLP 2021 Sparse Attention with Linear Units EMNLP 2021 SparseBERT: Rethinking the Importance Analysis in Self-attention ICML 2021 Sparse is Enough in Scaling Transformers NeurIPS 2021