Year: 2020
Type: conference-paper
Abstract: Simple yet effective data augmentation techniques have been proposed for sentence-level and sentence-pair natural language processing tasks.Inspired by these efforts, we design and compare data augmentation for named entity recognition, which is usually modeled as a token-level sequence labeling problem.Through experiments on two data sets from the biomedical and materials science domains (i2b2-2010 and MaSciP), we show that simple augmentation can boost performance for both recurrent and transformer-based models, especially for small training sets.
Authors: Xiang Dai, Heike Adel
Institutions: The University of Sydney, Data61, Robert Bosch (Germany)
Language: English
Topic: Topic Modeling
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W3115908473