exposure bia

Alleviating Exposure Bias via Multi-level Contrastive Learning and Deviation Simulation in Abstractive Summarization ACL 2023 Balancing Lexical and Semantic Quality in Abstractive Summarization ACL 2023 GPMO: Gradient Perturbation-Based Contrastive Learning for Molecule Optimization IJCAI 2023 Input Perturbation Reduces Exposure Bias in Diffusion Models ICML 2023 kNN-LM Does Not Improve Open-ended Text Generation EMNLP 2023 Mitigating Exposure Bias in Grammatical Error Correction with Data Augmentation and Reweighting EACL 2023 Mitigating the Exposure Bias in Sentence-Level Grapheme-to-Phoneme (G2P) Transduction Interspeech 2023 NewsDialogues: Towards Proactive News Grounded Conversation ACL 2023 Scaling Law for Document Neural Machine Translation EMNLP 2023 CoNT: Contrastive Neural Text Generation NeurIPS 2022 Improving Scheduled Sampling with Elastic Weight Consolidation for Neural Machine Translation EMNLP 2022 Keywords and Instances: A Hierarchical Contrastive Learning Framework Unifying Hybrid Granularities for Text Generation ACL 2022 Knowledge Infused Decoding ICLR 2022 Non-Autoregressive Sequence Generation ACL 2022 Rewarding Semantic Similarity under Optimized Alignments for AMR-to-Text Generation ACL 2022 R-TeaFor: Regularized Teacher-Forcing for Abstractive Summarization EMNLP 2022 Teacher Forcing Recovers Reward Functions for Text Generation NeurIPS 2022 Type-Driven Multi-Turn Corrections for Grammatical Error Correction ACL 2022 Why Exposure Bias Matters: An Imitation Learning Perspective of Error Accumulation in Language Generation ACL 2022 Adaptive Bridge between Training and Inference for Dialogue Generation EMNLP 2021 Contrastive Learning with Adversarial Perturbations for Conditional Text Generation ICLR 2021 Controlling Fairness and Bias in Dynamic Learning-to-Rank (Extended Abstract) IJCAI 2021 Correcting Exposure Bias for Link Recommendation ICML 2021 Discontinuous Named Entity Recognition as Maximal Clique Discovery ACL 2021 Exposure Bias versus Self-Recovery: Are Distortions Really Incremental for Autoregressive Text Generation? EMNLP 2021