Representation Learning

Surface Form Competition: Why the Highest Probability Answer Isn’t Always Right EMNLP 2021 Surrogate Gradient Field for Latent Space Manipulation CVPR 2021 Syntactically Diverse Adversarial Network for Knowledge-Grounded Conversation Generation EMNLP 2021 Syntactic Perturbations Reveal Representational Correlates of Hierarchical Phrase Structure in Pretrained Language Models ACL 2021 TearingNet: Point Cloud Autoencoder To Learn Topology-Friendly Representations CVPR 2021 Temporal Knowledge Consistency for Unsupervised Visual Representation Learning ICCV 2021 Temporally-Coherent Surface Reconstruction via Metric-Consistent Atlases ICCV 2021 Temporal Modulation Network for Controllable Space-Time Video Super-Resolution CVPR 2021 Test Harder than You Train: Probing with Extrapolation Splits EMNLP 2021 Text Style Transfer: Leveraging a Style Classifier on Entangled Latent Representations ACL 2021 The Case for Translation-Invariant Self-Attention in Transformer-Based Language Models ACL 2021 The Impact of Positional Encodings on Multilingual Compression EMNLP 2021 The Style-Content Duality of Attractiveness: Learning to Write Eye-Catching Headlines via Disentanglement AAAI 2021 The Value-Improvement Path: Towards Better Representations for Reinforcement Learning AAAI 2021 TIAGE: A Benchmark for Topic-Shift Aware Dialog Modeling EMNLP 2021 Time Adaptive Recurrent Neural Network CVPR 2021 Time-Aware Multi-Scale RNNs for Time Series Modeling IJCAI 2021 To be Closer: Learning to Link up Aspects with Opinions EMNLP 2021 Topological Relational Learning on Graphs NeurIPS 2021 Towards Balanced Defect Prediction with Better Information Propagation AAAI 2021 Towards Better Explanations of Class Activation Mapping ICCV 2021 Towards Label-Agnostic Emotion Embeddings EMNLP 2021 Towards Multi-Scale Style Control for Expressive Speech Synthesis Interspeech 2021 Towards Reusable Network Components by Learning Compatible Representations AAAI 2021 Towards robust vision by multi-task learning on monkey visual cortex NeurIPS 2021