@inproceedings{ruder-etal-2019-transfer,
title = "Transfer Learning in Natural Language Processing",
author = "Ruder, Sebastian and
Peters, Matthew E. and
Swayamdipta, Swabha and
Wolf, Thomas",
editor = "Sarkar, Anoop and
Strube, Michael",
booktitle = "Proceedings of the 2019 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Tutorials",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/N19-5004",
doi = "10.18653/v1/N19-5004",
pages = "15--18",
abstract = "The classic supervised machine learning paradigm is based on learning in isolation, a single predictive model for a task using a single dataset. This approach requires a large number of training examples and performs best for well-defined and narrow tasks. Transfer learning refers to a set of methods that extend this approach by leveraging data from additional domains or tasks to train a model with better generalization properties. Over the last two years, the field of Natural Language Processing (NLP) has witnessed the emergence of several transfer learning methods and architectures which significantly improved upon the state-of-the-art on a wide range of NLP tasks. These improvements together with the wide availability and ease of integration of these methods are reminiscent of the factors that led to the success of pretrained word embeddings and ImageNet pretraining in computer vision, and indicate that these methods will likely become a common tool in the NLP landscape as well as an important research direction. We will present an overview of modern transfer learning methods in NLP, how models are pre-trained, what information the representations they learn capture, and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ruder-etal-2019-transfer">
<titleInfo>
<title>Transfer Learning in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Ruder</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Matthew</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Peters</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Swabha</namePart>
<namePart type="family">Swayamdipta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thomas</namePart>
<namePart type="family">Wolf</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anoop</namePart>
<namePart type="family">Sarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Michael</namePart>
<namePart type="family">Strube</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>The classic supervised machine learning paradigm is based on learning in isolation, a single predictive model for a task using a single dataset. This approach requires a large number of training examples and performs best for well-defined and narrow tasks. Transfer learning refers to a set of methods that extend this approach by leveraging data from additional domains or tasks to train a model with better generalization properties. Over the last two years, the field of Natural Language Processing (NLP) has witnessed the emergence of several transfer learning methods and architectures which significantly improved upon the state-of-the-art on a wide range of NLP tasks. These improvements together with the wide availability and ease of integration of these methods are reminiscent of the factors that led to the success of pretrained word embeddings and ImageNet pretraining in computer vision, and indicate that these methods will likely become a common tool in the NLP landscape as well as an important research direction. We will present an overview of modern transfer learning methods in NLP, how models are pre-trained, what information the representations they learn capture, and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks.</abstract>
<identifier type="citekey">ruder-etal-2019-transfer</identifier>
<identifier type="doi">10.18653/v1/N19-5004</identifier>
<location>
<url>https://aclanthology.org/N19-5004</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>15</start>
<end>18</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Transfer Learning in Natural Language Processing
%A Ruder, Sebastian
%A Peters, Matthew E.
%A Swayamdipta, Swabha
%A Wolf, Thomas
%Y Sarkar, Anoop
%Y Strube, Michael
%S Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota
%F ruder-etal-2019-transfer
%X The classic supervised machine learning paradigm is based on learning in isolation, a single predictive model for a task using a single dataset. This approach requires a large number of training examples and performs best for well-defined and narrow tasks. Transfer learning refers to a set of methods that extend this approach by leveraging data from additional domains or tasks to train a model with better generalization properties. Over the last two years, the field of Natural Language Processing (NLP) has witnessed the emergence of several transfer learning methods and architectures which significantly improved upon the state-of-the-art on a wide range of NLP tasks. These improvements together with the wide availability and ease of integration of these methods are reminiscent of the factors that led to the success of pretrained word embeddings and ImageNet pretraining in computer vision, and indicate that these methods will likely become a common tool in the NLP landscape as well as an important research direction. We will present an overview of modern transfer learning methods in NLP, how models are pre-trained, what information the representations they learn capture, and review examples and case studies on how these models can be integrated and adapted in downstream NLP tasks.
%R 10.18653/v1/N19-5004
%U https://aclanthology.org/N19-5004
%U https://doi.org/10.18653/v1/N19-5004
%P 15-18
Markdown (Informal)
[Transfer Learning in Natural Language Processing](https://aclanthology.org/N19-5004) (Ruder et al., NAACL 2019)
ACL
- Sebastian Ruder, Matthew E. Peters, Swabha Swayamdipta, and Thomas Wolf. 2019. Transfer Learning in Natural Language Processing. In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Tutorials, pages 15–18, Minneapolis, Minnesota. Association for Computational Linguistics.