conftrace_

representation degeneration

10 papers

Explore in graph

Co-occurring keywords · papers mentioning both

contrastive learning (3) representation learning (3) language model (2) text generation (2) machine translation (2) angular distance (1) adaptive gradient gating (1) gradient gating (1) text novelty (1) self-attention anisotropy (1)

Papers

Reliable Clustering Number Estimation for Contrastive Multi-View Clustering CVPR 2026 Anisotropy Is Inherent to Self-Attention in Transformers EACL 2024 InvGC: Robust Cross-Modal Retrieval by Inverse Graph Convolution EMNLP 2023 Mitigating Data Imbalance and Representation Degeneration in Multilingual Machine Translation EMNLP 2023 Self-Weighted Contrastive Learning among Multiple Views for Mitigating Representation Degeneration NeurIPS 2023 Evade the Trap of Mediocrity: Promoting Diversity and Novelty in Text Generation via Concentrating Attention EMNLP 2022 Rare Tokens Degenerate All Tokens: Improving Neural Text Generation via Adaptive Gradient Gating for Rare Token Embeddings ACL 2022 A Cluster-based Approach for Improving Isotropy in Contextual Embedding Space ACL 2021 Improving Neural Language Generation with Spectrum Control ICLR 2020 Representation Degeneration Problem in Training Natural Language Generation Models ICLR 2019