Show newer
arXiv - CSCL

Sub-Task Decomposition Enables Learning in Sequence to Sequence Tasks. (arXiv:2204.02892v4 [cs.CL] UPDATED) 

arxiv.org/abs/2204.02892

0
arXiv - CSCL

Gold Doesn't Always Glitter: Spectral Removal of Linear and Nonlinear Guarded Attribute Information. (arXiv:2203.07893v2 [cs.CL] UPDATED) 

arxiv.org/abs/2203.07893

0
arXiv - CSCL

Improving Distantly-Supervised Named Entity Recognition with Self-Collaborative Denoising Learning. (arXiv:2110.04429v2 [cs.CL] UPDATED) 

arxiv.org/abs/2110.04429

0
arXiv - CSCL

ImaginE: An Imagination-Based Automatic Evaluation Metric for Natural Language Generation. (arXiv:2106.05970v3 [cs.CL] UPDATED) 

arxiv.org/abs/2106.05970

0
arXiv - CSCL

Sub-Character Tokenization for Chinese Pretrained Language Models. (arXiv:2106.00400v3 [cs.CL] UPDATED) 

arxiv.org/abs/2106.00400

0
arXiv - CSCL

Do Deep Neural Networks Capture Compositionality in Arithmetic Reasoning?. (arXiv:2302.07866v1 [cs.CL]) 

arxiv.org/abs/2302.07866

0
arXiv - CSCL

Big Little Transformer Decoder. (arXiv:2302.07863v1 [cs.CL]) 

arxiv.org/abs/2302.07863

0
arXiv - CSCL

Dictionary-based Phrase-level Prompting of Large Language Models for Machine Translation. (arXiv:2302.07856v1 [cs.CL]) 

arxiv.org/abs/2302.07856

0
arXiv - CSCL

NL2CMD: An Updated Workflow for Natural Language to Bash Commands Translation. (arXiv:2302.07845v1 [cs.CL]) 

arxiv.org/abs/2302.07845

0
arXiv - CSCL

Augmented Language Models: a Survey. (arXiv:2302.07842v1 [cs.CL]) 

arxiv.org/abs/2302.07842

0
arXiv - CSCL

Measuring the Instability of Fine-Tuning. (arXiv:2302.07778v1 [cs.CL]) 

arxiv.org/abs/2302.07778

0
arXiv - CSCL

Whats New? Identifying the Unfolding of New Events in Narratives. (arXiv:2302.07748v1 [cs.CL]) 

arxiv.org/abs/2302.07748

0
arXiv - CSCL

Team Triple-Check at Factify 2: Parameter-Efficient Large Foundation Models with Feature Representations for Multi-Modal Fact Verification. (arXiv:2302.07740v1 [cs.CL]) 

arxiv.org/abs/2302.07740

0
arXiv - CSCL

Meta-Learning Triplet Network with Adaptive Margins for Few-Shot Named Entity Recognition. (arXiv:2302.07739v1 [cs.CL]) 

arxiv.org/abs/2302.07739

0
arXiv - CSCL

Alloprof: a new French question-answer education dataset and its use in an information retrieval case study. (arXiv:2302.07738v1 [cs.CL]) 

arxiv.org/abs/2302.07738

0
arXiv - CSCL

Is ChatGPT better than Human Annotators? Potential and Limitations of ChatGPT in Explaining Implicit Hate Speech. (arXiv:2302.07736v1 [cs.CL]) 

arxiv.org/abs/2302.07736

0
arXiv - CSCL

Targeted Attack on GPT-Neo for the SATML Language Model Data Extraction Challenge. (arXiv:2302.07735v1 [cs.CL]) 

arxiv.org/abs/2302.07735

0
arXiv - CSCL

Explaining text classifiers through progressive neighborhood approximation with realistic samples. (arXiv:2302.07733v1 [cs.CL]) 

arxiv.org/abs/2302.07733

0
arXiv - CSCL

Combat AI With AI: Counteract Machine-Generated Fake Restaurant Reviews on Social Media. (arXiv:2302.07731v1 [cs.CL]) 

arxiv.org/abs/2302.07731

0
arXiv - CSCL

Transformer models: an introduction and catalog. (arXiv:2302.07730v1 [cs.CL]) 

arxiv.org/abs/2302.07730

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