Journal Article•
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
TL;DR: This article introduced a unified framework that converts all text-based language problems into a text-to-text format and compared pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks.
Abstract: Transfer learning, where a model is first pre-trained on a data-rich task before being fine-tuned on a downstream task, has emerged as a powerful technique in natural language processing (NLP). The effectiveness of transfer learning has given rise to a diversity of approaches, methodology, and practice. In this paper, we explore the landscape of transfer learning techniques for NLP by introducing a unified framework that converts all text-based language problems into a text-to-text format. Our systematic study compares pre-training objectives, architectures, unlabeled data sets, transfer approaches, and other factors on dozens of language understanding tasks. By combining the insights from our exploration with scale and our new ``Colossal Clean Crawled Corpus'', we achieve state-of-the-art results on many benchmarks covering summarization, question answering, text classification, and more. To facilitate future work on transfer learning for NLP, we release our data set, pre-trained models, and code.
Citations
More filters
Posted Content•
TL;DR: This paper developed a Retrieve-Generate-Filter (RGF) technique to create counterfactual evaluation and training data with minimal human supervision, using an open-domain QA framework and question generation model trained on original task data.
Abstract: Deep NLP models have been shown to learn spurious correlations, leaving them brittle to input perturbations. Recent work has shown that counterfactual or contrastive data -- i.e. minimally perturbed inputs -- can reveal these weaknesses, and that data augmentation using counterfactuals can help ameliorate them. Proposed techniques for generating counterfactuals rely on human annotations, perturbations based on simple heuristics, and meaning representation frameworks. We focus on the task of creating counterfactuals for question answering, which presents unique challenges related to world knowledge, semantic diversity, and answerability. To address these challenges, we develop a Retrieve-Generate-Filter(RGF) technique to create counterfactual evaluation and training data with minimal human supervision. Using an open-domain QA framework and question generation model trained on original task data, we create counterfactuals that are fluent, semantically diverse, and automatically labeled. Data augmentation with RGF counterfactuals improves performance on out-of-domain and challenging evaluation sets over and above existing methods, in both the reading comprehension and open-domain QA settings. Moreover, we find that RGF data leads to significant improvements in a model's robustness to local perturbations.
1 citations
Posted Content•
TL;DR: In this article, the authors show that existing software-based energy measurements are not accurate because they do not take into account hardware differences and how resource utilization affects energy consumption, and propose a more accurate energy estimation model that takes into account the hardware variabilities and the non-linear relationship between resource utilization and energy consumption.
Abstract: Accurate and reliable measurement of energy consumption is critical for making well-informed design choices when choosing and training large scale NLP models. In this work, we show that existing software-based energy measurements are not accurate because they do not take into account hardware differences and how resource utilization affects energy consumption. We conduct energy measurement experiments with four different models for a question answering task. We quantify the error of existing software-based energy measurements by using a hardware power meter that provides highly accurate energy measurements. Our key takeaway is the need for a more accurate energy estimation model that takes into account hardware variabilities and the non-linear relationship between resource utilization and energy consumption. We release the code and data at this https URL.
1 citations
Posted Content•
TL;DR: The authors empirically study and evaluate several factors that can affect performance on domain language applications, such as the sub-word vocabulary set, model size, pre-training corpus, and domain transfer, and show consistent improvements on benchmarks with their larger BioMegatron model trained on a larger domain corpus, contributing to their understanding of domain language model applications.
Abstract: There has been an influx of biomedical domain-specific language models, showing language models pre-trained on biomedical text perform better on biomedical domain benchmarks than those trained on general domain text corpora such as Wikipedia and Books. Yet, most works do not study the factors affecting each domain language application deeply. Additionally, the study of model size on domain-specific models has been mostly missing. We empirically study and evaluate several factors that can affect performance on domain language applications, such as the sub-word vocabulary set, model size, pre-training corpus, and domain transfer. We show consistent improvements on benchmarks with our larger BioMegatron model trained on a larger domain corpus, contributing to our understanding of domain language model applications. We demonstrate noticeable improvements over the previous state-of-the-art (SOTA) on standard biomedical NLP benchmarks of named entity recognition, relation extraction, and question answering. Model checkpoints and code are available at [this https URL] and [this https URL].
1 citations
Posted Content•
TL;DR: LiST as mentioned in this paper uses self-training in conjunction with meta-learning for reweighting noisy pseudo-prompt labels, which not only improves the model performance for few-shot learning on target domains but also reduces the model memory footprint.
Abstract: We present a new method LiST for efficient fine-tuning of large pre-trained language models (PLMs) in few-shot learning settings. LiST significantly improves over recent methods that adopt prompt fine-tuning using two key techniques. The first one is the use of self-training to leverage large amounts of unlabeled data for prompt-tuning to significantly boost the model performance in few-shot settings. We use self-training in conjunction with meta-learning for re-weighting noisy pseudo-prompt labels. However, traditional self-training is expensive as it requires updating all the model parameters repetitively. Therefore, we use a second technique for light-weight fine-tuning where we introduce a small number of task-specific adapter parameters that are fine-tuned during self-training while keeping the PLM encoder frozen. This also significantly reduces the overall model footprint across several tasks that can now share a common PLM encoder as backbone for inference. Combining the above techniques, LiST not only improves the model performance for few-shot learning on target domains but also reduces the model memory footprint. We present a comprehensive study on six NLU tasks to validate the effectiveness of LiST. The results show that LiST improves by 35% over classic fine-tuning methods and 6% over prompt-tuning with 96% reduction in number of trainable parameters when fine-tuned with no more than 30 labeled examples from each target domain.
1 citations
Proceedings Article•
01 Nov 2021
TL;DR: CoCoNet as mentioned in this paper enhances the standard copying mechanism by keeping track of the copying history and explicitly encourages the model to copy the input word that is relevant to the previously copied one.
Abstract: The copying mechanism has had considerable success in abstractive summarization, facilitating models to directly copy words from the input text to the output summary. Existing works mostly employ encoder-decoder attention, which applies copying at each time step independently of the former ones. However, this may sometimes lead to incomplete copying. In this paper, we propose a novel copying scheme named Correlational Copying Network (CoCoNet) that enhances the standard copying mechanism by keeping track of the copying history. It thereby takes advantage of prior copying distributions and, at each time step, explicitly encourages the model to copy the input word that is relevant to the previously copied one. In addition, we strengthen CoCoNet through pre-training with suitable corpora that simulate the copying behaviors. Experimental results show that CoCoNet can copy more accurately and achieves new state-of-the-art performances on summarization benchmarks, including CNN/DailyMail for news summarization and SAMSum for dialogue summarization. The code and checkpoint will be publicly available.
1 citations