scispace - formally typeset
Search or ask a question
Journal Article

Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer

TL;DR: 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.

Content maybe subject to copyright    Report

Citations
More filters
Proceedings ArticleDOI
01 Jun 2021
TL;DR: A new Massive Open Online Course on Natural Language Processing, targeted at non-English speaking students, designed to familirize students with the core concepts and methods in NLP, and show that recent advances are build upon these concepts.
Abstract: In this paper we present a new Massive Open Online Course on Natural Language Processing, targeted at non-English speaking students. The course lasts 12 weeks, every week consists of lectures, practical sessions and quiz assigments. Three weeks out of 12 are followed by Kaggle-style coding assigments. Our course intents to serve multiple purposes: (i) familirize students with the core concepts and methods in NLP, such as language modelling or word or sentence representations, (ii) show that recent advances, including pre-trained Transformer-based models, are build upon these concepts; (iii) to introduce architectures for most most demanded real-life applications, (iii) to develop practical skills to process texts in multiple languages. The course was prepared and recorded during 2020 and so far have received positive feedback.

2 citations

Posted Content
TL;DR: The authors show that running DADC over many rounds maximizes its training-time benefits, as the different rounds can together cover many of the task-relevant phenomena, and they show that training on adversarial data yields examples that are more difficult, more lexically and syntactically diverse, and contain fewer annotation artifacts compared to non-adversarial examples.
Abstract: To create models that are robust across a wide range of test inputs, training datasets should include diverse examples that span numerous phenomena. Dynamic adversarial data collection (DADC), where annotators craft examples that challenge continually improving models, holds promise as an approach for generating such diverse training sets. Prior work has shown that running DADC over 1-3 rounds can help models fix some error types, but it does not necessarily lead to better generalization beyond adversarial test data. We argue that running DADC over many rounds maximizes its training-time benefits, as the different rounds can together cover many of the task-relevant phenomena. We present the first study of longer-term DADC, where we collect 20 rounds of NLI examples for a small set of premise paragraphs, with both adversarial and non-adversarial approaches. Models trained on DADC examples make 26% fewer errors on our expert-curated test set compared to models trained on non-adversarial data. Our analysis shows that DADC yields examples that are more difficult, more lexically and syntactically diverse, and contain fewer annotation artifacts compared to non-adversarial examples.

2 citations

Posted Content
TL;DR: This paper proposed a large-scale, natural, and diverse question-answering dataset for open-domain question answering (ODQA) using the Common Crawl Question Answering dataset (CCQA).
Abstract: With the rise of large-scale pre-trained language models, open-domain question-answering (ODQA) has become an important research topic in NLP. Based on the popular pre-training fine-tuning approach, we posit that an additional in-domain pre-training stage using a large-scale, natural, and diverse question-answering (QA) dataset can be beneficial for ODQA. Consequently, we propose a novel QA dataset based on the Common Crawl project in this paper. Using the readily available this http URL annotation, we extract around 130 million multilingual question-answer pairs, including about 60 million English data-points. With this previously unseen number of natural QA pairs, we pre-train popular language models to show the potential of large-scale in-domain pre-training for the task of question-answering. In our experiments, we find that pre-training question-answering models on our Common Crawl Question Answering dataset (CCQA) achieves promising results in zero-shot, low resource and fine-tuned settings across multiple tasks, models and benchmarks.

2 citations

Proceedings Article
02 Sep 2021
TL;DR: The MultiI-EURLEX dataset as discussed by the authors contains 65k European Union (EU) laws, annotated with multiple labels from the EUROVOC taxonomy and used as a testbed for zero-shot cross-lingual transfer.
Abstract: We introduce MULTI-EURLEX, a new multilingual dataset for topic classification of legal documents. The dataset comprises 65k European Union (EU) laws, officially translated in 23 languages, annotated with multiple labels from the EUROVOC taxonomy. We highlight the effect of temporal concept drift and the importance of chronological, instead of random splits. We use the dataset as a testbed for zero-shot cross-lingual transfer, where we exploit annotated training documents in one language (source) to classify documents in another language (target). We find that fine-tuning a multilingually pretrained model (XLM-ROBERTA, MT5) in a single source language leads to catastrophic forgetting of multilingual knowledge and, consequently, poor zero-shot transfer to other languages. Adaptation strategies, namely partial fine-tuning, adapters, BITFIT, LNFIT, originally proposed to accelerate fine-tuning for new end-tasks, help retain multilingual knowledge from pretraining, substantially improving zero-shot cross-lingual transfer, but their impact also depends on the pretrained model used and the size of the label set.

2 citations

DOI
16 Nov 2021
TL;DR: The current fight against COVID-19 is not only around its prevention and cure but also about mitigating the negative impact resulting from misinformation around it as discussed by the authors. But the pervasiveness of socia...
Abstract: The current fight against COVID-19 is not only around its prevention and cure but it is also about mitigating the negative impact resulting from misinformation around it. The pervasiveness of socia...

2 citations

Trending Questions (1)
What are the limitations of transfer learning with a unified text-to-text transformer?

The paper does not mention the limitations of transfer learning with a unified text-to-text transformer.