Techniques

Anatomy of Catastrophic Forgetting: Hidden Representations and Task Semantics ICLR 2021 An Edge-Enhanced Hierarchical Graph-to-Tree Network for Math Word Problem Solving EMNLP 2021 An Efficient Streaming Non-Recurrent On-Device End-to-End Model with Improvements to Rare-Word Modeling Interspeech 2021 An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls NAACL 2021 An Empirical Investigation of Word Alignment Supervision for Zero-Shot Multilingual Neural Machine Translation EMNLP 2021 A Neural Graph-based Local Coherence Model EMNLP 2021 An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale ICLR 2021 An Improved Wav2Vec 2.0 Pre-Training Approach Using Enhanced Local Dependency Modeling for Speech Recognition Interspeech 2021 Annealing Knowledge Distillation EACL 2021 An Optimistic Acceleration of AMSGrad for Nonconvex Optimization ACML 2021 Any-Precision Deep Neural Networks AAAI 2021 Anytime Inference with Distilled Hierarchical Neural Ensembles AAAI 2021 APGN: Adversarial and Parameter Generation Networks for Multi-Source Cross-Domain Dependency Parsing EMNLP 2021 Appending Adversarial Frames for Universal Video Attack WACV 2021 Approximating Lipschitz continuous functions with GroupSort neural networks AISTATS 2021 A Practical Method for Constructing Equivariant Multilayer Perceptrons for Arbitrary Matrix Groups ICML 2021 A Pre-training Strategy for Zero-Resource Response Selection in Knowledge-Grounded Conversations ACL 2021 ArabicTransformer: Efficient Large Arabic Language Model with Funnel Transformer and ELECTRA Objective EMNLP 2021 A Recipe for Global Convergence Guarantee in Deep Neural Networks AAAI 2021 Are Pretrained Convolutions Better than Pretrained Transformers? ACL 2021 Argument Pair Extraction via Attention-guided Multi-Layer Multi-Cross Encoding ACL 2021 ARMAN: Pre-training with Semantically Selecting and Reordering of Sentences for Persian Abstractive Summarization EMNLP 2021 A Robust and Efficient Framework for Sports-Field Registration WACV 2021 Artificial Text Detection via Examining the Topology of Attention Maps EMNLP 2021 A Simple and Effective Positional Encoding for Transformers EMNLP 2021