Show newer
arXiv - CSCL

Unifying Vision, Text, and Layout for Universal Document Processing. (arXiv:2212.02623v1 [cs.CV]) 

arxiv.org/abs/2212.02623

0
arXiv - CSCL

Fine-tuning a Subtle Parsing Distinction Using a Probabilistic Decision Tree: the Case of Postnominal "that" in Noun Complement Clauses vs. Relative Clauses. (arXiv:2212.02591v1 [cs.CL]) 

arxiv.org/abs/2212.02591

0
arXiv - CSCL

INCLUSIFY: A benchmark and a model for gender-inclusive German. (arXiv:2212.02564v1 [cs.CL]) 

arxiv.org/abs/2212.02564

0
arXiv - CSCL

Cross-Domain Few-Shot Relation Extraction via Representation Learning and Domain Adaptation. (arXiv:2212.02560v1 [cs.CL]) 

arxiv.org/abs/2212.02560

0
arXiv - CSCL

Masked Contrastive Pre-Training for Efficient Video-Text Retrieval. (arXiv:2212.00986v2 [cs.CV] UPDATED) 

arxiv.org/abs/2212.00986

0
arXiv - CSCL

End-to-End Neural Discourse Deixis Resolution in Dialogue. (arXiv:2211.15980v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.15980

0
arXiv - CSCL

Frustratingly Easy Label Projection for Cross-lingual Transfer. (arXiv:2211.15613v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.15613

0
arXiv - CSCL

A Report on the Euphemisms Detection Shared Task. (arXiv:2211.13327v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.13327

0
arXiv - CSCL

Multitask Vision-Language Prompt Tuning. (arXiv:2211.11720v3 [cs.CV] UPDATED) 

arxiv.org/abs/2211.11720

0
arXiv - CSCL

Parameter-Efficient Tuning on Layer Normalization for Pre-trained Language Models. (arXiv:2211.08682v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.08682

0
arXiv - CSCL

Discourse and conversation impairments in patients with dementia. (arXiv:2211.07971v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.07971

0
arXiv - CSCL

EVA: Exploring the Limits of Masked Visual Representation Learning at Scale. (arXiv:2211.07636v2 [cs.CV] UPDATED) 

arxiv.org/abs/2211.07636

0
arXiv - CSCL

Comparative layer-wise analysis of self-supervised speech models. (arXiv:2211.03929v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.03929

0
arXiv - CSCL

ERNIE-SAT: Speech and Text Joint Pretraining for Cross-Lingual Multi-Speaker Text-to-Speech. (arXiv:2211.03545v2 [eess.AS] UPDATED) 

arxiv.org/abs/2211.03545

0
arXiv - CSCL

Evaluation of Automated Speech Recognition Systems for Conversational Speech: A Linguistic Perspective. (arXiv:2211.02812v2 [cs.CL] UPDATED) 

arxiv.org/abs/2211.02812

0
arXiv - CSCL

Why is Winoground Hard? Investigating Failures in Visuolinguistic Compositionality. (arXiv:2211.00768v4 [cs.CL] UPDATED) 

arxiv.org/abs/2211.00768

0
arXiv - CSCL

Learning New Tasks from a Few Examples with Soft-Label Prototypes. (arXiv:2210.17437v2 [cs.LG] UPDATED) 

arxiv.org/abs/2210.17437

0
arXiv - CSCL

Topical Segmentation of Spoken Narratives: A Test Case on Holocaust Survivor Testimonies. (arXiv:2210.13783v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.13783

0
arXiv - CSCL

RARR: Researching and Revising What Language Models Say, Using Language Models. (arXiv:2210.08726v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.08726

0
arXiv - CSCL

Guess the Instruction! Flipped Learning Makes Language Models Stronger Zero-Shot Learners. (arXiv:2210.02969v3 [cs.CL] UPDATED) 

arxiv.org/abs/2210.02969

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