conftrace_
← Keywords

knowledge distillation

3725 papers

Explore in graph

Also known as

KD

Co-occurring keywords

model compression (3302) large language model (13587) transfer learning (5449) domain adaptation (4595) representation learning (6206) neural network (6616) language model (4599) catastrophic forgetting (958) continual learning (1181) contrastive learning (4032)

Papers

Trigger is Not Sufficient: Exploiting Frame-aware Knowledge for Implicit Event Argument Extraction ACL 2021
Towards Quantifiable Dialogue Coherence Evaluation IJCNLP 2021
ESPnet-ST IWSLT 2021 Offline Speech Translation System ACL 2021
Claim Matching Beyond English to Scale Global Fact-Checking ACL 2021
Matching Distributions between Model and Data: Cross-domain Knowledge Distillation for Unsupervised Domain Adaptation ACL 2021
Rejuvenating Low-Frequency Words: Making the Most of Parallel Data in Non-Autoregressive Translation ACL 2021
Towards Quantifiable Dialogue Coherence Evaluation ACL 2021
TAILOR: Teaching with Active and Incremental Learning for Object Registration AAAI 2021
A Student-Teacher Architecture for Dialog Domain Adaptation Under the Meta-Learning Setting AAAI 2021
Distilling the Knowledge of Large-scale Generative Models into Retrieval Models for Efficient Open-domain Conversation EMNLP 2021
GPT3Mix: Leveraging Large-scale Language Models for Text Augmentation EMNLP 2021
Block Pruning For Faster Transformers EMNLP 2021
Students Who Study Together Learn Better: On the Importance of Collective Knowledge Distillation for Domain Transfer in Fact Verification EMNLP 2021
Towards Zero-Shot Knowledge Distillation for Natural Language Processing EMNLP 2021
HRKD: Hierarchical Relational Knowledge Distillation for Cross-domain Language Model Compression EMNLP 2021
Distilling Linguistic Context for Language Model Compression EMNLP 2021
POS-Constrained Parallel Decoding for Non-autoregressive Generation ACL 2021
Enhanced Audio Tagging via Multi- to Single-Modal Teacher-Student Mutual Learning AAAI 2021
The USYD-JD Speech Translation System for IWSLT2021 ACL 2021
Deeplite NeutrinoTM: A BlackBox Framework for Constrained Deep Learning Model Optimization AAAI 2021
Split-and-Bridge: Adaptable Class Incremental Learning within a Single Neural Network AAAI 2021
Cross-model Back-translated Distillation for Unsupervised Machine Translation ICML 2021
Knowledge Refinery: Learning from Decoupled Label AAAI 2021
Probabilistic Model Distillation for Semantic Correspondence CVPR 2021
Delving into Data: Effectively Substitute Training for Black-box Attack CVPR 2021