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
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
Journal ArticleDOI
Automated fact-checking: A survey
TL;DR: The authors reviewed relevant research on automated fact-checking covering both the claim detection and claim validation components, and proposed NLP methods to further research in the development of different components, including claim validation and claim detection.
Proceedings ArticleDOI
Precise Task Formalization Matters in Winograd Schema Evaluations
TL;DR: This work performs an ablation on two Winograd Schema datasets that interpolates between the formalizations used before and after this surge, and finds framing the task as multiple choice improves performance by 2-6 points and several additional techniques can mitigate the model's extreme sensitivity to hyperparameters.
Posted Content
WordCraft: An Environment for Benchmarking Commonsense Agents.
Minqi Jiang,Jelena Luketina,Nantas Nardelli,Pasquale Minervini,Philip H. S. Torr,Shimon Whiteson,Tim Rocktäschel +6 more
TL;DR: This work proposes WordCraft, an RL environment based on Little Alchemy 2.0 that is fast to run and built upon entities and relations inspired by real-world semantics, and evaluates several representation learning methods on this new benchmark and proposes a new method for integrating knowledge graphs with an RL agent.
Proceedings ArticleDOI
Select, Substitute, Search: A New Benchmark for Knowledge-Augmented Visual Question Answering
Aman Jain,Mayank Kothyari,Vishwajeet Kumar,Preethi Jyothi,Ganesh Ramakrishnan,Soumen Chakrabarti +5 more
TL;DR: The authors identify a key structural idiom in OKVQA, S3 (select, substitute and search), and build a new data set and challenge around it, which can be used to assess the ability to integrate cross-modal information.
Posted Content
Cross-Task Generalization via Natural Language Crowdsourcing Instructions
TL;DR: NATURAL INSTRUCTIONS as mentioned in this paper is a dataset of 61 distinct tasks, their human-authored instructions and 193k task instances, obtained from crowdsourcing instructions used to collect existing NLP datasets and mapped to a unified schema.