Show newer
arXiv - CSCL

Mathematically Modeling the Lexicon Entropy of Emergent Language. (arXiv:2211.15783v1 [cs.CL]) 

arxiv.org/abs/2211.15783

0
arXiv - CSCL

Controlled Language Generation for Language Learning Items. (arXiv:2211.15731v1 [cs.CL]) 

arxiv.org/abs/2211.15731

0
arXiv - CSCL

CoNAL: Anticipating Outliers with Large Language Models. (arXiv:2211.15718v1 [cs.CL]) 

arxiv.org/abs/2211.15718

0
arXiv - CSCL

Hey ASR System! Why Aren't You More Inclusive? Automatic Speech Recognition Systems' Bias and Proposed Bias Mitigation Techniques. A Literature Review. (arXiv:2211.09511v1 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2211.09511

0
arXiv - CSCL

Acceptability Judgements via Examining the Topology of Attention Maps. (arXiv:2205.09630v2 [cs.CL] CROSS LISTED) 

arxiv.org/abs/2205.09630

0
arXiv - CSCL

L3Cube-HindBERT and DevBERT: Pre-Trained BERT Transformer models for Devanagari based Hindi and Marathi Languages. (arXiv:2211.11418v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.11418

0
arXiv - CSCL

SmoothQuant: Accurate and Efficient Post-Training Quantization for Large Language Models. (arXiv:2211.10438v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.10438

0
arXiv - CSCL

BERT on a Data Diet: Finding Important Examples by Gradient-Based Pruning. (arXiv:2211.05610v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.05610

0
arXiv - CSCL

Speech separation with large-scale self-supervised learning. (arXiv:2211.05172v2 [eess.AS] UPDATED) 

arxiv.org/abs/2211.05172

0
arXiv - CSCL

Intriguing Properties of Compression on Multilingual Models. (arXiv:2211.02738v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.02738

0
arXiv - CSCL

LVP-M3: Language-aware Visual Prompt for Multilingual Multimodal Machine Translation. (arXiv:2210.15461v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.15461

0
arXiv - CSCL

ReAct: Synergizing Reasoning and Acting in Language Models. (arXiv:2210.03629v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.03629

0
arXiv - CSCL

Memory in humans and deep language models: Linking hypotheses for model augmentation. (arXiv:2210.01869v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.01869

0
arXiv - CSCL

An Attention Matrix for Every Decision: Faithfulness-based Arbitration Among Multiple Attention-Based Interpretations of Transformers in Text Classification. (arXiv:2209.10876v2 [cs.CL] UPDATED) 

arxiv.org/abs/2209.10876

0
arXiv - CSCL

ConvNeXt Based Neural Network for Audio Anti-Spoofing. (arXiv:2209.06434v4 [cs.SD] UPDATED) 

arxiv.org/abs/2209.06434

0
arXiv - CSCL

Extend and Explain: Interpreting Very Long Language Models. (arXiv:2209.01174v3 [cs.CL] UPDATED) 

arxiv.org/abs/2209.01174

0
arXiv - CSCL

Induced Natural Language Rationales and Interleaved Markup Tokens Enable Extrapolation in Large Language Models. (arXiv:2208.11445v3 [cs.CL] UPDATED) 

arxiv.org/abs/2208.11445

0
arXiv - CSCL

Unit Testing for Concepts in Neural Networks. (arXiv:2208.10244v2 [cs.CL] UPDATED) 

arxiv.org/abs/2208.10244

0
arXiv - CSCL

GSRFormer: Grounded Situation Recognition Transformer with Alternate Semantic Attention Refinement. (arXiv:2208.08965v4 [cs.CV] UPDATED) 

arxiv.org/abs/2208.08965

0
arXiv - CSCL

u-HuBERT: Unified Mixed-Modal Speech Pretraining And Zero-Shot Transfer to Unlabeled Modality. (arXiv:2207.07036v2 [cs.CL] UPDATED) 

arxiv.org/abs/2207.07036

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