Show newer
arXiv - CSCL

Rethinking and Improving Multi-task Learning for End-to-end Speech Translation. (arXiv:2311.03810v1 [cs.CL]) 

arxiv.org/abs/2311.03810

0
arXiv - CSCL

Noisy Pair Corrector for Dense Retrieval. (arXiv:2311.03798v1 [cs.CL]) 

arxiv.org/abs/2311.03798

0
arXiv - CSCL

Character-Level Bangla Text-to-IPA Transcription Using Transformer Architecture with Sequence Alignment. (arXiv:2311.03792v1 [cs.CL]) 

arxiv.org/abs/2311.03792

0
arXiv - CSCL

Language Representation Projection: Can We Transfer Factual Knowledge across Languages in Multilingual Language Models?. (arXiv:2311.03788v1 [cs.CL]) 

arxiv.org/abs/2311.03788

0
arXiv - CSCL

Ensembling Textual and Structure-Based Models for Knowledge Graph Completion. (arXiv:2311.03780v1 [cs.CL]) 

arxiv.org/abs/2311.03780

0
arXiv - CSCL

Gender Inflected or Bias Inflicted: On Using Grammatical Gender Cues for Bias Evaluation in Machine Translation. (arXiv:2311.03767v1 [cs.CL]) 

arxiv.org/abs/2311.03767

0
arXiv - CSCL

Multilingual Mathematical Autoformalization. (arXiv:2311.03755v1 [cs.CL]) 

arxiv.org/abs/2311.03755

0
arXiv - CSCL

Which is better? Exploring Prompting Strategy For LLM-based Metrics. (arXiv:2311.03754v1 [cs.CL]) 

arxiv.org/abs/2311.03754

0
arXiv - CSCL

COOL: A Constraint Object-Oriented Logic Programming Language and its Neural-Symbolic Compilation System. (arXiv:2311.03753v1 [cs.AI]) 

arxiv.org/abs/2311.03753

0
arXiv - CSCL

Unified Low-Resource Sequence Labeling by Sample-Aware Dynamic Sparse Finetuning. (arXiv:2311.03748v1 [cs.CL]) 

arxiv.org/abs/2311.03748

0
arXiv - CSCL

Leveraging Structured Information for Explainable Multi-hop Question Answering and Reasoning. (arXiv:2311.03734v1 [cs.CL]) 

arxiv.org/abs/2311.03734

0
arXiv - CSCL

Learning to Learn for Few-shot Continual Active Learning. (arXiv:2311.03732v1 [cs.LG]) 

arxiv.org/abs/2311.03732

0
arXiv - CSCL

A Survey of Large Language Models Attribution. (arXiv:2311.03731v1 [cs.CL]) 

arxiv.org/abs/2311.03731

0
arXiv - CSCL

LLM as an Art Director (LaDi): Using LLMs to improve Text-to-Media Generators. (arXiv:2311.03716v1 [cs.CL]) 

arxiv.org/abs/2311.03716

0
arXiv - CSCL

Bilingual Corpus Mining and Multistage Fine-Tuning for Improving Machine Translation of Lecture Transcripts. (arXiv:2311.03696v1 [cs.CL]) 

arxiv.org/abs/2311.03696

0
arXiv - CSCL

Dissecting the Runtime Performance of the Training, Fine-tuning, and Inference of Large Language Models. (arXiv:2311.03687v1 [cs.PF]) 

arxiv.org/abs/2311.03687

0
arXiv - CSCL

CBSiMT: Mitigating Hallucination in Simultaneous Machine Translation with Weighted Prefix-to-Prefix Training. (arXiv:2311.03672v1 [cs.CL]) 

arxiv.org/abs/2311.03672

0
arXiv - CSCL

Generalization of NLP Models: Notion and Causation. (arXiv:2311.03663v1 [cs.CL]) 

arxiv.org/abs/2311.03663

0
arXiv - CSCL

The Linear Representation Hypothesis and the Geometry of Large Language Models. (arXiv:2311.03658v1 [cs.CL]) 

arxiv.org/abs/2311.03658

0
arXiv - CSCL

Innovation and Word Usage Patterns in Machine Learning. (arXiv:2311.03633v1 [cs.LG]) 

arxiv.org/abs/2311.03633

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.

Resources

Developers

What is Mastodon?

qoto.org

More…

v3.5.19-qoto · Privacy policy