Show newer
arXiv - CSCL

Tail Batch Sampling: Approximating Global Contrastive Losses as Optimization over Batch Assignments. (arXiv:2210.12874v2 [cs.LG] UPDATED) 

arxiv.org/abs/2210.12874

0
arXiv - CSCL

Generative Knowledge Graph Construction: A Review. (arXiv:2210.12714v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.12714

0
arXiv - CSCL

Textual Entailment Recognition with Semantic Features from Empirical Text Representation. (arXiv:2210.09723v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.09723

0
arXiv - CSCL

A Unified Encoder-Decoder Framework with Entity Memory. (arXiv:2210.03273v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.03273

0
arXiv - CSCL

Improving Mandarin Speech Recogntion with Block-augmented Transformer. (arXiv:2207.11697v5 [cs.CL] UPDATED) 

arxiv.org/abs/2207.11697

0
arXiv - CSCL

Approximate Conditional Coverage & Calibration via Neural Model Approximations. (arXiv:2205.14310v3 [cs.LG] UPDATED) 

arxiv.org/abs/2205.14310

0
arXiv - CSCL

ATTEMPT: Parameter-Efficient Multi-task Tuning via Attentional Mixtures of Soft Prompts. (arXiv:2205.11961v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.11961

0
arXiv - CSCL

ColBERT: Using BERT Sentence Embedding in Parallel Neural Networks for Computational Humor. (arXiv:2004.12765v7 [cs.CL] UPDATED) 

arxiv.org/abs/2004.12765

0
arXiv - CSCL

Simplifying and Understanding State Space Models with Diagonal Linear RNNs. (arXiv:2212.00768v1 [cs.LG]) 

arxiv.org/abs/2212.00768

0
arXiv - CSCL

Improving astroBERT using Semantic Textual Similarity. (arXiv:2212.00744v1 [cs.CL]) 

arxiv.org/abs/2212.00744

0
arXiv - CSCL

What do you MEME? Generating Explanations for Visual Semantic Role Labelling in Memes. (arXiv:2212.00715v1 [cs.CY]) 

arxiv.org/abs/2212.00715

0
arXiv - CSCL

CliMedBERT: A Pre-trained Language Model for Climate and Health-related Text. (arXiv:2212.00689v1 [cs.CL]) 

arxiv.org/abs/2212.00689

0
arXiv - CSCL

Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis. (arXiv:2212.00678v1 [cs.CL]) 

arxiv.org/abs/2212.00678

0
arXiv - CSCL

Analyzing the State of Computer Science Research with the DBLP Discovery Dataset. (arXiv:2212.00629v1 [cs.DL]) 

arxiv.org/abs/2212.00629

0
arXiv - CSCL

Extensible Prompts for Language Models. (arXiv:2212.00616v1 [cs.CL]) 

arxiv.org/abs/2212.00616

0
arXiv - CSCL

Language models and brain alignment: beyond word-level semantics and prediction. (arXiv:2212.00596v1 [cs.CL]) 

arxiv.org/abs/2212.00596

0
arXiv - CSCL

Embedding generation for text classification of Brazilian Portuguese user reviews: from bag-of-words to transformers. (arXiv:2212.00587v1 [cs.CL]) 

arxiv.org/abs/2212.00587

0
arXiv - CSCL

Long-Document Cross-Lingual Summarization. (arXiv:2212.00586v1 [cs.CL]) 

arxiv.org/abs/2212.00586

0
arXiv - CSCL

Research on the application of contrastive learning in multi-label text classification. (arXiv:2212.00552v1 [cs.CL]) 

arxiv.org/abs/2212.00552

0
arXiv - CSCL

CultureBERT: Fine-Tuning Transformer-Based Language Models for Corporate Culture. (arXiv:2212.00509v1 [cs.CL]) 

arxiv.org/abs/2212.00509

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