transformer architecture

Attention is Turing-Complete JMLR 2021 Attention Weights in Transformer NMT Fail Aligning Words Between Sequences but Largely Explain Model Predictions EMNLP 2021 Autoformer: Decomposition Transformers with Auto-Correlation for Long-Term Series Forecasting NeurIPS 2021 BabyBERTa: Learning More Grammar With Small-Scale Child-Directed Language CoNLL 2021 BERT Goes Shopping: Comparing Distributional Models for Product Representations ACL 2021 BERTology Meets Biology: Interpreting Attention in Protein Language Models ICLR 2021 BERT Prescriptions to Avoid Unwanted Headaches: A Comparison of Transformer Architectures for Adverse Drug Event Detection EACL 2021 Capturing Row and Column Semantics in Transformer Based Question Answering over Tables NAACL 2021 *-CFQ: Analyzing the Scalability of Machine Learning on a Compositional Task AAAI 2021 Changing the Basis of Contextual Representations with Explicit Semantics ACL 2021 Cloud Transformers: A Universal Approach to Point Cloud Processing Tasks ICCV 2021 Co-evolution Transformer for Protein Contact Prediction NeurIPS 2021 CogView: Mastering Text-to-Image Generation via Transformers NeurIPS 2021 Combiner: Full Attention Transformer with Sparse Computation Cost NeurIPS 2021 Comparison of Grammatical Error Correction Using Back-Translation Models NAACL 2021 Compositional Transformers for Scene Generation NeurIPS 2021 Condenser: a Pre-training Architecture for Dense Retrieval EMNLP 2021 ConQuest: Contextual Question Paraphrasing through Answer-Aware Synthetic Question Generation EMNLP 2021 Container: Context Aggregation Networks NeurIPS 2021 Conversational Multi-Hop Reasoning with Neural Commonsense Knowledge and Symbolic Logic Rules EMNLP 2021 CoreLM: Coreference-aware Language Model Fine-Tuning EMNLP 2021 CoRT: Complementary Rankings from Transformers NAACL 2021 COTR: Correspondence Transformer for Matching Across Images ICCV 2021 CTRL-C: Camera Calibration TRansformer With Line-Classification ICCV 2021 Decision Transformer: Reinforcement Learning via Sequence Modeling NeurIPS 2021