It's Not Just Size That Matters: Small Language Models Are Also Few-Shot Learners

TL;DR: A novel contrastive framework for IDRR that effectively incorporates global and local hierarchies of senses to learn better discourse relation representations.

TL;DR: This paper designs pathological demonstrations by gradually removing intuitively useful information from the standard ones to take a deep dive of the robustness of demonstration-based sequence labeling and shows that demonstrations composed of random tokens still make the model a better few-shot learner.

TL;DR: This paper proposed a data and compute efficient self-supervised, contrastive text encoder, pretrained on 60MB of ''task-internal'' text data, and compare it to RoBERTa, which was pretrained over 160GB of 'task-external' text.

TL;DR: In this paper , the authors highlight several alternatives to dataset balancing, focusing on enhancing datasets with richer contexts, allowing models to abstain and interact with users, and turning from large-scale fine-tuning to zero- or few-shot setups.

TL;DR: A new language representation model, BERT, designed to pre-train deep bidirectional representations from unlabeled text by jointly conditioning on both left and right context in all layers, which can be fine-tuned with just one additional output layer to create state-of-the-art models for a wide range of tasks.

Abstract: The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism. We propose a new simple network architecture, the Transformer, based solely on attention mechanisms, dispensing with recurrence and convolutions entirely. Experiments on two machine translation tasks show these models to be superior in quality while being more parallelizable and requiring significantly less time to train. Our model achieves 28.4 BLEU on the WMT 2014 English-to-German translation task, improving over the existing best results, including ensembles by over 2 BLEU. On the WMT 2014 English-to-French translation task, our model establishes a new single-model state-of-the-art BLEU score of 41.8 after training for 3.5 days on eight GPUs, a small fraction of the training costs of the best models from the literature. We show that the Transformer generalizes well to other tasks by applying it successfully to English constituency parsing both with large and limited training data.

TL;DR: It is found that BERT was significantly undertrained, and can match or exceed the performance of every model published after it, and the best model achieves state-of-the-art results on GLUE, RACE and SQuAD.

TL;DR: GPT-3 achieves strong performance on many NLP datasets, including translation, question-answering, and cloze tasks, as well as several tasks that require on-the-fly reasoning or domain adaptation, such as unscrambling words, using a novel word in a sentence, or performing 3-digit arithmetic.