논문 (21) 썸네일형 리스트형 [논문 공부] What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers 원문 : https://arxiv.org/pdf/2109.04650.pdf 개요 이번 포스팅에서는 What Changes Can Large-scale Language Models Bring? Intensive Study on HyperCLOVA: Billions-scale Korean Generative Pretrained Transformers 논문을 공부합니다. 나는 사용했다. 구글 번역기 번역을 위해서 Reference jiho님의 HyperCLOVA .. [논문 공부] What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis [논문 공부] What Is Wrong With Scene Text Recognition Model Comparisons Dataset and Model Analysis 원문 : https://arxiv.org/abs/1904.01906 What Is Wrong With Scene Text Recognition Model Comparisons? Dataset and Model Analysis Many new proposals for scene text recognition (STR) models have been introduced in recent years. While each claim to have pushed the boundary of the technology, a holistic and f.. [논문 공부] CRAFT : Character Region Awareness for Text Detection [논문 공부] Character Region Awareness for Text Detection 원문 : https://arxiv.org/abs/1904.01941 Character Region Awareness for Text Detection Scene text detection methods based on neural networks have emerged recently and have shown promising results. Previous methods trained with rigid word-level bounding boxes exhibit limitations in representing the text region in an arbitrary shape. In this p arx.. [논문 공부] Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism 원문 : https://arxiv.org/abs/1909.08053 Megatron-LM: Training Multi-Billion Parameter Language Models Using Model Parallelism Recent work in language modeling demonstrates that training large transformer models advances the state of the art in Natural Language Processing applications. However, very large models can be quite difficult to train due to memory constraints. In this wo arxiv.org 개요 이번 포.. [논문 공부] LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention [논문 공부] LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention 원문 : https://arxiv.org/abs/2010.01057 LUKE: Deep Contextualized Entity Representations with Entity-aware Self-attention Entity representations are useful in natural language tasks involving entities. In this paper, we propose new pretrained contextualized representations of words and entities based on the b.. [논문 공부] BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension [논문 공부] BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension 원문 : https://arxiv.org/abs/1910.13461 BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension We present BART, a denoising autoencoder for pretraining sequence-to-sequence models. BART is trained by (1) corrupting text.. [논문 공부] ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators 원문 : https://arxiv.org/abs/2003.10555 ELECTRA: Pre-training Text Encoders as Discriminators Rather Than Generators Masked language modeling (MLM) pre-training methods such as BERT corrupt the input by replacing some tokens with [MASK] and then train a model to reconstruct the original tokens. While they produce good res.. [논문 공부] ALBERT : A LITE BERT FOR SELF-SUPERVISED LEARNING OF LANGUAGE REPRESENTATIONS [논문 공부] ALBERT : A Lite BERT for Self-supervised Learning of Language Representations 원문 : https://arxiv.org/abs/1909.11942 ALBERT: A Lite BERT for Self-supervised Learning of Language Representations Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due t.. 이전 1 2 3 다음
