Show newer
arXiv - CSCL

Efficient Self-supervised Learning with Contextualized Target Representations for Vision, Speech and Language. (arXiv:2212.07525v2 [cs.LG] UPDATED) 

arxiv.org/abs/2212.07525

0
arXiv - CSCL

Inconsistency Ranking-based Noisy Label Detection for High-quality Data. (arXiv:2212.00239v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.00239

0
arXiv - CSCL

Reducing Hallucinations in Neural Machine Translation with Feature Attribution. (arXiv:2211.09878v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.09878

0
arXiv - CSCL

ATCO2 corpus: A Large-Scale Dataset for Research on Automatic Speech Recognition and Natural Language Understanding of Air Traffic Control Communications. (arXiv:2211.04054v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.04054

0
arXiv - CSCL

PromptCast: A New Prompt-based Learning Paradigm for Time Series Forecasting. (arXiv:2210.08964v3 [stat.ME] UPDATED) 

arxiv.org/abs/2210.08964

0
arXiv - CSCL

MAMO: Masked Multimodal Modeling for Fine-Grained Vision-Language Representation Learning. (arXiv:2210.04183v3 [cs.CV] UPDATED) 

arxiv.org/abs/2210.04183

0
arXiv - CSCL

SpeechLM: Enhanced Speech Pre-Training with Unpaired Textual Data. (arXiv:2209.15329v3 [cs.CL] UPDATED) 

arxiv.org/abs/2209.15329

0
arXiv - CSCL

Learning Dynamic Contextualised Word Embeddings via Template-based Temporal Adaptation. (arXiv:2208.10734v3 [cs.CL] UPDATED) 

arxiv.org/abs/2208.10734

0
arXiv - CSCL

PLAtE: A Large-scale Dataset for List Page Web Extraction. (arXiv:2205.12386v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.12386

0
arXiv - CSCL

A Taxonomy of Prompt Modifiers for Text-To-Image Generation. (arXiv:2204.13988v3 [cs.MM] UPDATED) 

arxiv.org/abs/2204.13988

0
arXiv - CSCL

Detection of sepsis during emergency department triage using machine learning. (arXiv:2204.07657v6 [cs.LG] UPDATED) 

arxiv.org/abs/2204.07657

0
arXiv - CSCL

Focusing on Potential Named Entities During Active Label Acquisition. (arXiv:2111.03837v3 [cs.CL] UPDATED) 

arxiv.org/abs/2111.03837

0
arXiv - CSCL

Self-conditioning pre-trained language models. (arXiv:2110.02802v4 [cs.CL] UPDATED) 

arxiv.org/abs/2110.02802

0
arXiv - CSCL

WARM: A Weakly (+Semi) Supervised Model for Solving Math word Problems. (arXiv:2104.06722v2 [cs.CL] UPDATED) 

arxiv.org/abs/2104.06722

0
arXiv - CSCL

Contrastive Loss is All You Need to Recover Analogies as Parallel Lines. (arXiv:2306.08221v1 [cs.CL]) 

arxiv.org/abs/2306.08221

0
arXiv - CSCL

Operationalising Representation in Natural Language Processing. (arXiv:2306.08193v1 [cs.CL]) 

arxiv.org/abs/2306.08193

0
arXiv - CSCL

Assessing the Effectiveness of GPT-3 in Detecting False Political Statements: A Case Study on the LIAR Dataset. (arXiv:2306.08190v1 [cs.CL]) 

arxiv.org/abs/2306.08190

0
arXiv - CSCL

Language models are not naysayers: An analysis of language models on negation benchmarks. (arXiv:2306.08189v1 [cs.CL]) 

arxiv.org/abs/2306.08189

0
arXiv - CSCL

INT2.1: Towards Fine-Tunable Quantized Large Language Models with Error Correction through Low-Rank Adaptation. (arXiv:2306.08162v1 [cs.CL]) 

arxiv.org/abs/2306.08162

0
arXiv - CSCL

h2oGPT: Democratizing Large Language Models. (arXiv:2306.08161v1 [cs.CL]) 

arxiv.org/abs/2306.08161

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