Show newer
arXiv - CSCL

StrAE: Autoencoding for Pre-Trained Embeddings using Explicit Structure. (arXiv:2305.05588v1 [cs.CL]) 

arxiv.org/abs/2305.05588

0
arXiv - CSCL

Large Language Models Humanize Technology. (arXiv:2305.05576v1 [cs.CL]) 

arxiv.org/abs/2305.05576

0
arXiv - CSCL

Exploiting Pseudo Image Captions for Multimodal Summarization. (arXiv:2305.05496v1 [cs.CL]) 

arxiv.org/abs/2305.05496

0
arXiv - CSCL

MAUPQA: Massive Automatically-created Polish Question Answering Dataset. (arXiv:2305.05486v1 [cs.CL]) 

arxiv.org/abs/2305.05486

0
arXiv - CSCL

Investigating the effect of sub-word segmentation on the performance of transformer language models. (arXiv:2305.05480v1 [cs.CL]) 

arxiv.org/abs/2305.05480

0
arXiv - CSCL

Going beyond research datasets: Novel intent discovery in the industry setting. (arXiv:2305.05474v1 [cs.CL]) 

arxiv.org/abs/2305.05474

0
arXiv - CSCL

Beyond Good Intentions: Reporting the Research Landscape of NLP for Social Good. (arXiv:2305.05471v1 [cs.CL]) 

arxiv.org/abs/2305.05471

0
arXiv - CSCL

What is the best recipe for character-level encoder-only modelling?. (arXiv:2305.05461v1 [cs.CL]) 

arxiv.org/abs/2305.05461

0
arXiv - CSCL

WikiWeb2M: A Page-Level Multimodal Wikipedia Dataset. (arXiv:2305.05432v1 [cs.CL]) 

arxiv.org/abs/2305.05432

0
arXiv - CSCL

Estimating related words computationally using language model from the Mahabharata - an Indian epic. (arXiv:2305.05420v1 [cs.CL]) 

arxiv.org/abs/2305.05420

0
arXiv - CSCL

Large Language Models Need Holistically Thought in Medical Conversational QA. (arXiv:2305.05410v1 [cs.CL]) 

arxiv.org/abs/2305.05410

0
arXiv - CSCL

Completeness, Recall, and Negation in Open-World Knowledge Bases: A Survey. (arXiv:2305.05403v1 [cs.AI]) 

arxiv.org/abs/2305.05403

0
arXiv - CSCL

Consistent Text Categorization using Data Augmentation in e-Commerce. (arXiv:2305.05402v1 [cs.LG]) 

arxiv.org/abs/2305.05402

0
arXiv - CSCL

CaseEncoder: A Knowledge-enhanced Pre-trained Model for Legal Case Encoding. (arXiv:2305.05393v1 [cs.IR]) 

arxiv.org/abs/2305.05393

0
arXiv - CSCL

COKE: A Cognitive Knowledge Graph for Machine Theory of Mind. (arXiv:2305.05390v1 [cs.CL]) 

arxiv.org/abs/2305.05390

0
arXiv - CSCL

Code Execution with Pre-trained Language Models. (arXiv:2305.05383v1 [cs.PL]) 

arxiv.org/abs/2305.05383

0
arXiv - CSCL

PLM-GNN: A Webpage Classification Method based on Joint Pre-trained Language Model and Graph Neural Network. (arXiv:2305.05378v1 [cs.CL]) 

arxiv.org/abs/2305.05378

0
arXiv - CSCL

Large Language Model Programs. (arXiv:2305.05364v1 [cs.LG]) 

arxiv.org/abs/2305.05364

0
arXiv - CSCL

A Framework for Designing Foundation Model based Systems. (arXiv:2305.05352v1 [cs.SE]) 

arxiv.org/abs/2305.05352

0
arXiv - CSCL

Rudolf Christoph Eucken at SemEval-2023 Task 4: An Ensemble Approach for Identifying Human Values from Arguments. (arXiv:2305.05335v1 [cs.CL]) 

arxiv.org/abs/2305.05335

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