Show newer

HunSum-1: an Abstractive Summarization Dataset for Hungarian. (arXiv:2302.00455v1 [cs.CL]) 

Improved Knowledge Distillation for Pre-trained Language Models via Knowledge Selection. (arXiv:2302.00444v1 [cs.CL]) 

KNNs of Semantic Encodings for Rating Prediction. (arXiv:2302.00412v1 [cs.CL]) 

On the Role of Morphological Information for Contextual Lemmatization. (arXiv:2302.00407v1 [cs.CL]) 

mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video. (arXiv:2302.00402v1 [cs.CV]) 

An Empirical Study on the Transferability of Transformer Modules in Parameter-Efficient Fine-Tuning. (arXiv:2302.00378v1 [cs.CL]) 

Attention Link: An Efficient Attention-Based Low Resource Machine Translation Architecture. (arXiv:2302.00340v1 [cs.CL]) 

Evaluating TCFD Reporting: A New Application of Zero-Shot Analysis to Climate-Related Financial Disclosures. (arXiv:2302.00326v1 [cs.CY]) 

An Evaluation of Persian-English Machine Translation Datasets with Transformers. (arXiv:2302.00321v1 [cs.CL]) 

Filtering Context Mitigates Scarcity and Selection Bias in Political Ideology Prediction. (arXiv:2302.00239v1 [cs.LG]) 

A Transaction Represented with Weighted Finite-State Transducers. (arXiv:2302.00200v1 [cs.FL]) 

Detecting Lexical Borrowings from Dominant Languages in Multilingual Wordlists. (arXiv:2302.00189v1 [cs.CL]) 

Program Generation from Diverse Video Demonstrations. (arXiv:2302.00178v1 [cs.CV]) 

Universal Topological Regularities of Syntactic Structures: Decoupling Efficiency from Optimization. (arXiv:2302.00129v1 [cs.CL]) 

Machine Translation Impact in E-commerce Multilingual Search. (arXiv:2302.00119v1 [cs.CL]) 

Detecting Harmful Agendas in News Articles. (arXiv:2302.00102v1 [cs.CL]) 

Large Language Models Can Be Easily Distracted by Irrelevant Context. (arXiv:2302.00093v1 [cs.CL]) 

In-Context Retrieval-Augmented Language Models. (arXiv:2302.00083v1 [cs.CL]) 

The Power of External Memory in Increasing Predictive Model Capacity. (arXiv:2302.00003v1 [cs.LG]) 

Large Language Models Are Implicitly Topic Models: Explaining and Finding Good Demonstrations for In-Context Learning. (arXiv:2301.11916v1 [cs.CL] CROSS LISTED) 

Show older
Qoto Mastodon

QOTO: Question Others to Teach Ourselves
An inclusive, Academic Freedom, instance
All cultures welcome.
Hate speech and harassment strictly forbidden.