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
CANDLE: Decomposing Conditional and Conjunctive Queries for Task-Oriented Dialogue Systems.
TL;DR: The authors decompose complex queries composed of conditional and sequential clauses that represent multiple actions into smaller single-action sub-queries that are reasonable for intent classifiers to understand in a dialogue pipeline.
Posted Content
Scalable Fact-checking with Human-in-the-Loop.
TL;DR: In this paper, a set of social media posts (e.g., tweets) are cleaned and a graph of all posts based on their semantics is constructed for further claim summarization.
Posted Content
Question Answering over Electronic Devices: A New Benchmark Dataset and a Multi-Task Learning based QA Framework
TL;DR: In this article, the authors proposed EMQAP (E-Manual Question Answering Pipeline) that answers questions pertaining to electronics devices using a supervised multi-task learning framework which efficiently performs the dual tasks of identifying the section in the E-manual where the answer can be found and the exact answer span within that section.
Posted Content
Improving Paraphrase Detection with the Adversarial Paraphrasing Task
Animesh Nighojkar,John Licato +1 more
TL;DR: The adversarial paraphrase task (APT) as discussed by the authors ) is a dataset that asks participants to generate semantically equivalent (in the sense of mutually implicative) but lexically and syntactically disparate paraphrases, which can then be used both to test paraphrase identification models and then improve their performance.