Σχετικά με το έγγραφο αυτό
- sl:arxiv_author :
- sl:arxiv_firstAuthor : Michael A. Hedderich
- sl:arxiv_num : 2010.12309
- sl:arxiv_published : 2020-10-23T11:22:01Z
- sl:arxiv_summary : Deep neural networks and huge language models are becoming omnipresent in
natural language applications. As they are known for requiring large amounts of
training data, there is a growing body of work to improve the performance in
low-resource settings. Motivated by the recent fundamental changes towards
neural models and the popular pre-train and fine-tune paradigm, we survey
promising approaches for low-resource natural language processing. After a
discussion about the different dimensions of data availability, we give a
structured overview of methods that enable learning when training data is
sparse. This includes mechanisms to create additional labeled data like data
augmentation and distant supervision as well as transfer learning settings that
reduce the need for target supervision. A goal of our survey is to explain how
these methods differ in their requirements as understanding them is essential
for choosing a technique suited for a specific low-resource setting. Further
key aspects of this work are to highlight open issues and to outline promising
directions for future research.@en
- sl:arxiv_title : A Survey on Recent Approaches for Natural Language Processing in Low-Resource Scenarios@en
- sl:arxiv_updated : 2021-04-09T13:48:02Z
- sl:bookmarkOf : https://arxiv.org/abs/2010.12309
- sl:creationDate : 2021-07-06
- sl:creationTime : 2021-07-06T13:08:01Z
Προτιμήσεις...