Show newer
arXiv - CSCL

Recurrent Memory Transformer. (arXiv:2207.06881v2 [cs.CL] UPDATED) 

arxiv.org/abs/2207.06881

0
arXiv - CSCL

Know Where You're Going: Meta-Learning for Parameter-Efficient Fine-Tuning. (arXiv:2205.12453v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.12453

0
arXiv - CSCL

Measuring Context-Word Biases in Lexical Semantic Datasets. (arXiv:2112.06733v4 [cs.CL] UPDATED) 

arxiv.org/abs/2112.06733

0
arXiv - CSCL

Reinforcement Learning for Few-Shot Text Generation Adaptation. (arXiv:2111.11030v3 [cs.CL] UPDATED) 

arxiv.org/abs/2111.11030

0
arXiv - CSCL

Confounds and Overestimations in Fake Review Detection: Experimentally Controlling for Product-Ownership and Data-Origin. (arXiv:2110.15130v2 [cs.CL] UPDATED) 

arxiv.org/abs/2110.15130

0
arXiv - CSCL

Improving Named Entity Recognition by External Context Retrieving and Cooperative Learning. (arXiv:2105.03654v3 [cs.CL] UPDATED) 

arxiv.org/abs/2105.03654

0
arXiv - CSCL

OFASys: A Multi-Modal Multi-Task Learning System for Building Generalist Models. (arXiv:2212.04408v1 [cs.CV]) 

arxiv.org/abs/2212.04408

0
arXiv - CSCL

BEVBert: Topo-Metric Map Pre-training for Language-guided Navigation. (arXiv:2212.04385v1 [cs.CV]) 

arxiv.org/abs/2212.04385

0
arXiv - CSCL

Robust Speech Recognition via Large-Scale Weak Supervision. (arXiv:2212.04356v1 [eess.AS]) 

arxiv.org/abs/2212.04356

0
arXiv - CSCL

Implicit causality in GPT-2: a case study. (arXiv:2212.04348v1 [cs.CL]) 

arxiv.org/abs/2212.04348

0
arXiv - CSCL

Lattice-Free Sequence Discriminative Training for Phoneme-Based Neural Transducers. (arXiv:2212.04325v1 [eess.AS]) 

arxiv.org/abs/2212.04325

0
arXiv - CSCL

Montague semantics and modifier consistency measurement in neural language models. (arXiv:2212.04310v1 [cs.CL]) 

arxiv.org/abs/2212.04310

0
arXiv - CSCL

Lie detection algorithms attract few users but vastly increase accusation rates. (arXiv:2212.04277v1 [econ.GN]) 

arxiv.org/abs/2212.04277

0
arXiv - CSCL

A Modality-level Explainable Framework for Misinformation Checking in Social Networks. (arXiv:2212.04272v1 [cs.LG]) 

arxiv.org/abs/2212.04272

0
arXiv - CSCL

ConsistTL: Modeling Consistency in Transfer Learning for Low-Resource Neural Machine Translation. (arXiv:2212.04262v1 [cs.CL]) 

arxiv.org/abs/2212.04262

0
arXiv - CSCL

Momentum Calibration for Text Generation. (arXiv:2212.04257v1 [cs.CL]) 

arxiv.org/abs/2212.04257

0
arXiv - CSCL

Harnessing the Power of Multi-Task Pretraining for Ground-Truth Level Natural Language Explanations. (arXiv:2212.04231v1 [cs.CV]) 

arxiv.org/abs/2212.04231

0
arXiv - CSCL

The Neural Correlates of Linguistic Structure Building: Comments on Kazanina & Tavano (2022). (arXiv:2212.04219v1 [cs.CL]) 

arxiv.org/abs/2212.04219

0
arXiv - CSCL

Scientific Paper Extractive Summarization Enhanced by Citation Graphs. (arXiv:2212.04214v1 [cs.CL]) 

arxiv.org/abs/2212.04214

0
arXiv - CSCL

DC-MBR: Distributional Cooling for Minimum Bayesian Risk Decoding. (arXiv:2212.04205v1 [cs.CL]) 

arxiv.org/abs/2212.04205

0
Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.

Trending now

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy