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
Proceedings ArticleDOI
Can I be of further assistance? Using unstructured knowledge access to improve task-oriented conversational modeling
TL;DR: In this article, a pipelined approach is proposed for knowledge-seeking turn detection, knowledge selection, and response generation in sequence, which achieves state-of-the-art performance on the DSTC9 Track 1 benchmark dataset.
Posted Content
Delphi: Towards Machine Ethics and Norms
Liwei Jiang,Jena D. Hwang,Chandra Bhagavatula,Ronan Le Bras,Maxwell Forbes,Jon Borchardt,Jenny Liang,Oren Etzioni,Maarten Sap,Yejin Choi +9 more
TL;DR: The authors used commonsense reasoning to anticipate the outcome of alternative actions in different contexts, and demonstrated strong promise of language-based commonsense moral reasoning with up to 92.1% accuracy vetted by humans.
Posted Content
Detecting Hate Speech with GPT-3.
Ke-Li Chiu,Rohan Alexander +1 more
TL;DR: The authors used GPT-3 to identify sexist and racist text passages with zero-, one-, and few-shot learning, with an accuracy between 48% and 69% with few shot learning.
Posted Content
Improving Pretrained Cross-Lingual Language Models via Self-Labeled Word Alignment
TL;DR: The authors introduced denoising word alignment as a new cross-lingual pre-training task, where the model first self-labels word alignments for parallel sentences and then randomly mask tokens in a bite-xt pair.
Proceedings Article
A Generative Framework for Simultaneous Machine Translation
TL;DR: The authors proposed a generative framework for simultaneous machine translation, where a latent variable is introduced to model read or translate actions at every time step, which is then integrated out to consider all the possible translation policies.