Show newer
arXiv - CSCL

Prompt-Tuning Can Be Much Better Than Fine-Tuning on Cross-lingual Understanding With Multilingual Language Models. (arXiv:2210.12360v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.12360

0
arXiv - CSCL

Rethinking Round-Trip Translation for Machine Translation Evaluation. (arXiv:2209.07351v2 [cs.CL] UPDATED) 

arxiv.org/abs/2209.07351

0
arXiv - CSCL

CORAL: Contextual Response Retrievability Loss Function for Training Dialog Generation Models. (arXiv:2205.10558v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.10558

0
arXiv - CSCL

HighMMT: Quantifying Modality & Interaction Heterogeneity for High-Modality Representation Learning. (arXiv:2203.01311v3 [cs.LG] UPDATED) 

arxiv.org/abs/2203.01311

0
arXiv - CSCL

Fine-Tuning Transformers: Vocabulary Transfer. (arXiv:2112.14569v2 [cs.CL] UPDATED) 

arxiv.org/abs/2112.14569

0
arXiv - CSCL

Textless Speech Emotion Conversion using Discrete and Decomposed Representations. (arXiv:2111.07402v3 [cs.CL] UPDATED) 

arxiv.org/abs/2111.07402

0
arXiv - CSCL

QA-GNN: Reasoning with Language Models and Knowledge Graphs for Question Answering. (arXiv:2104.06378v5 [cs.CL] UPDATED) 

arxiv.org/abs/2104.06378

0
arXiv - CSCL

RT-1: Robotics Transformer for Real-World Control at Scale. (arXiv:2212.06817v1 [cs.RO]) 

arxiv.org/abs/2212.06817

0
arXiv - CSCL

A fine-grained comparison of pragmatic language understanding in humans and language models. (arXiv:2212.06801v1 [cs.CL]) 

arxiv.org/abs/2212.06801

0
arXiv - CSCL

Diverse Demonstrations Improve In-context Compositional Generalization. (arXiv:2212.06800v1 [cs.CL]) 

arxiv.org/abs/2212.06800

0
arXiv - CSCL

Earthquake Impact Analysis Based on Text Mining and Social Media Analytics. (arXiv:2212.06765v1 [cs.CL]) 

arxiv.org/abs/2212.06765

0
arXiv - CSCL

ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages. (arXiv:2212.06742v1 [cs.CL]) 

arxiv.org/abs/2212.06742

0
arXiv - CSCL

The Turing Deception. (arXiv:2212.06721v1 [cs.LG]) 

arxiv.org/abs/2212.06721

0
arXiv - CSCL

Structured Prompting: Scaling In-Context Learning to 1,000 Examples. (arXiv:2212.06713v1 [cs.CL]) 

arxiv.org/abs/2212.06713

0
arXiv - CSCL

On Text-based Personality Computing: Challenges and Future Directions. (arXiv:2212.06711v1 [cs.CL]) 

arxiv.org/abs/2212.06711

0
arXiv - CSCL

Do Text-to-Text Multi-Task Learners Suffer from Task Conflict?. (arXiv:2212.06645v1 [cs.CL]) 

arxiv.org/abs/2212.06645

0
arXiv - CSCL

Categorical Tools for Natural Language Processing. (arXiv:2212.06636v1 [cs.CL]) 

arxiv.org/abs/2212.06636

0
arXiv - CSCL

Category Theory for Quantum Natural Language Processing. (arXiv:2212.06615v1 [math.CT]) 

arxiv.org/abs/2212.06615

0
arXiv - CSCL

Exploring Fake News Detection with Heterogeneous Social Media Context Graphs. (arXiv:2212.06560v1 [cs.CL]) 

arxiv.org/abs/2212.06560

0
arXiv - CSCL

Localized Latent Updates for Fine-Tuning Vision-Language Models. (arXiv:2212.06556v1 [cs.CV]) 

arxiv.org/abs/2212.06556

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