Show newer
arXiv - CSCL

Democratizing Neural Machine Translation with OPUS-MT. (arXiv:2212.01936v2 [cs.CL] UPDATED) 

arxiv.org/abs/2212.01936

0
arXiv - CSCL

Model and Data Transfer for Cross-Lingual Sequence Labelling in Zero-Resource Settings. (arXiv:2210.12623v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.12623

0
arXiv - CSCL

Communication breakdown: On the low mutual intelligibility between human and neural captioning. (arXiv:2210.11512v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.11512

0
arXiv - CSCL

Context Generation Improves Open Domain Question Answering. (arXiv:2210.06349v2 [cs.CL] UPDATED) 

arxiv.org/abs/2210.06349

0
arXiv - CSCL

The Parallelism Tradeoff: Limitations of Log-Precision Transformers. (arXiv:2207.00729v4 [cs.CC] UPDATED) 

arxiv.org/abs/2207.00729

0
arXiv - CSCL

PREME: Preference-based Meeting Exploration through an Interactive Questionnaire. (arXiv:2205.02370v2 [cs.CL] UPDATED) 

arxiv.org/abs/2205.02370

0
arXiv - CSCL

BiTimeBERT: Extending Pre-Trained Language Representations with Bi-Temporal Information. (arXiv:2204.13032v4 [cs.CL] UPDATED) 

arxiv.org/abs/2204.13032

0
arXiv - CSCL

GrIPS: Gradient-free, Edit-based Instruction Search for Prompting Large Language Models. (arXiv:2203.07281v2 [cs.CL] UPDATED) 

arxiv.org/abs/2203.07281

0
arXiv - CSCL

ViMQ: A Vietnamese Medical Question Dataset for Healthcare Dialogue System Development. (arXiv:2304.14405v1 [cs.CL]) 

arxiv.org/abs/2304.14405

0
arXiv - CSCL

LaMini-LM: A Diverse Herd of Distilled Models from Large-Scale Instructions. (arXiv:2304.14402v1 [cs.CL]) 

arxiv.org/abs/2304.14402

0
arXiv - CSCL

We're Afraid Language Models Aren't Modeling Ambiguity. (arXiv:2304.14399v1 [cs.CL]) 

arxiv.org/abs/2304.14399

0
arXiv - CSCL

string2string: A Modern Python Library for String-to-String Algorithms. (arXiv:2304.14395v1 [cs.CL]) 

arxiv.org/abs/2304.14395

0
arXiv - CSCL

Energy-based Models as Zero-Shot Planners for Compositional Scene Rearrangement. (arXiv:2304.14391v1 [cs.RO]) 

arxiv.org/abs/2304.14391

0
arXiv - CSCL

CONSCENDI: A Contrastive and Scenario-Guided Distillation Approach to Guardrail Models for Virtual Assistants. (arXiv:2304.14364v1 [cs.CL]) 

arxiv.org/abs/2304.14364

0
arXiv - CSCL

Industrial Engineering with Large Language Models: A case study of ChatGPT's performance on Oil & Gas problems. (arXiv:2304.14354v1 [cs.CL]) 

arxiv.org/abs/2304.14354

0
arXiv - CSCL

The Dark Side of ChatGPT: Legal and Ethical Challenges from Stochastic Parrots and Hallucination. (arXiv:2304.14347v1 [cs.CY]) 

arxiv.org/abs/2304.14347

0
arXiv - CSCL

MarsEclipse at SemEval-2023 Task 3: Multi-Lingual and Multi-Label Framing Detection with Contrastive Learning. (arXiv:2304.14339v1 [cs.CL]) 

arxiv.org/abs/2304.14339

0
arXiv - CSCL

Idioms, Probing and Dangerous Things: Towards Structural Probing for Idiomaticity in Vector Space. (arXiv:2304.14333v1 [cs.CL]) 

arxiv.org/abs/2304.14333

0
arXiv - CSCL

q2d: Turning Questions into Dialogs to Teach Models How to Search. (arXiv:2304.14318v1 [cs.CL]) 

arxiv.org/abs/2304.14318

0
arXiv - CSCL

Large Language Models Are State-of-the-Art Evaluators of Code Generation. (arXiv:2304.14317v1 [cs.AI]) 

arxiv.org/abs/2304.14317

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