Open AccessJournal Article
Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
Colin Raffel,Noam Shazeer,Adam Roberts,Katherine Lee,Sharan Narang,Michael Matena,Yanqi Zhou,Wei Li,Peter J. Liu +8 more
Reads0
Chats0
TLDR
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.read more
Citations
More filters
Posted Content
Reinforcement Learning for Abstractive Question Summarization with Question-aware Semantic Rewards
TL;DR: In this article, a reinforcement learning-based framework for abstractive question summarization is introduced. But, the task of summarization of long questions is a challenging task due to the lack of training data and the complexity of related subtasks, such as the question focus and type recognition.
Proceedings Article
Query Expansion with Semantic-Based Ellipsis Reduction for Conversational IR.
Posted Content
Learning Neural Models for Natural Language Processing in the Face of Distributional Shift
TL;DR: This paper proposed a new gradient update rule to mitigate the effect of distributional shift on NLP models and developed methods based on parametric reformulations of the distributionally robust optimization framework.
Posted Content
Crossing the Format Boundary of Text and Boxes: Towards Unified Vision-Language Modeling
Zhengyuan Yang,Zhe Gan,Jianfeng Wang,Xiaowei Hu,Faisal Ahmed,Zicheng Liu,Yumao Lu,Lijuan Wang +7 more
TL;DR: UNICORN as discussed by the authors unifies text generation and bounding box prediction into a single architecture by quantizing each box into four discrete box tokens and serializing them as a sequence, which can be integrated with text tokens.
Book ChapterDOI
Counterfactual Retrieval for Augmentation and Decisions.
Nwaike Kelechi,Shuang Geng +1 more
TL;DR: In this paper, the authors explore user generated counterfactual tweets and by aggregating counter-factual statements that relate to pre-determined keywords, CORFAD simplifies data analysis by suggesting variables towards which future actions might have the greater or lesser effects towards a defined goal.