Pretraining

Dorylus: Affordable, Scalable, and Accurate GNN Training with Distributed CPU Servers and Serverless Threads OSDI 2021 DyLex: Incorporating Dynamic Lexicons into BERT for Sequence Labeling EMNLP 2021 ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning EMNLP 2021 Effective Sequence-to-Sequence Dialogue State Tracking EMNLP 2021 Efficiently Summarizing Text and Graph Encodings of Multi-Document Clusters NAACL 2021 Efficient Visual Pretraining With Contrastive Detection ICCV 2021 eMLM: A New Pre-training Objective for Emotion Related Tasks ACL 2021 Emotion Recognition from Speech Using wav2vec 2.0 Embeddings Interspeech 2021 EmpathBERT: A BERT-based Framework for Demographic-aware Empathy Prediction EACL 2021 E(n) Equivariant Graph Neural Networks ICML 2021 Entity at SemEval-2021 Task 5: Weakly Supervised Token Labelling for Toxic Spans Detection SemEval 2021 Entity-level Cross-modal Learning Improves Multi-modal Machine Translation EMNLP 2021 ERNIE-Gram: Pre-Training with Explicitly N-Gram Masked Language Modeling for Natural Language Understanding NAACL 2021 ERNIE-M: Enhanced Multilingual Representation by Aligning Cross-lingual Semantics with Monolingual Corpora EMNLP 2021 ERNIE-ViL: Knowledge Enhanced Vision-Language Representations through Scene Graphs AAAI 2021 EventHPE: Event-Based 3D Human Pose and Shape Estimation ICCV 2021 Explaining Self-Supervised Image Representations with Visual Probing IJCAI 2021 Explicit Alignment Objectives for Multilingual Bidirectional Encoders NAACL 2021 Exploration and Exploitation: Two Ways to Improve Chinese Spelling Correction Models ACL 2021 Exploring Metaphoric Paraphrase Generation CoNLL 2021 Exploring the Limits of Out-of-Distribution Detection NeurIPS 2021 Extracting Zero-shot Structured Information from Form-like Documents: Pretraining with Keys and Triggers AAAI 2021 FairFil: Contrastive Neural Debiasing Method for Pretrained Text Encoders ICLR 2021 FAME: Feature-Based Adversarial Meta-Embeddings for Robust Input Representations EMNLP 2021 Fast Training of Neural Lumigraph Representations using Meta Learning NeurIPS 2021