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
Enhancing Transformers with Gradient Boosted Decision Trees for NLI Fine-Tuning
TL;DR: This article proposed Gradient Boosted Decision Trees (GBDTs) as an alternative to the commonly used Multi-Layer Perceptron (MLP) classification head for small Natural Language Inference (NLI) datasets.
Posted Content
An Optimized Dataflow for Mitigating Attention Performance Bottlenecks
TL;DR: In this article, a new attention-tailored dataflow, termed FLAT, which identifies fusion opportunities within the attention layer, and implements an on-chip memory-aware interleaved execution and tiling mechanism.
Posted Content
How Reliable are Model Diagnostics
TL;DR: The authors examine three recent diagnostic tests for pre-trained language models, and find that likelihood-based and representation-based model diagnostics are not yet as reliable as previously assumed, and formulate recommendations for practitioners and researchers.
Proceedings ArticleDOI
TellMeWhy: A Dataset for Answering Why-Questions in Narratives
TL;DR: In this article, the authors introduce a new crowd-sourced dataset that consists of more than 30k questions and free-form answers concerning why characters in short narratives perform the actions described.
Proceedings Article
ConvFiT: Conversational Fine-Tuning of Pretrained Language Models
Ivan Vulić,Pei-Hao Su,Sam Coope,Daniela Gerz,Paweł Budzianowski,Iñigo Casanueva,Nikola Mrkšić,Tsung-Hsien Wen +7 more
TL;DR: This paper proposed ConvFiT, a simple and efficient two-stage procedure which turns any pretrained LM into a universal conversational encoder and task-specialised sentence encoder, respectively.