English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

In this paper, we address the problem of effectively self-training neuralnetworks in a low-resource setting. Self-training is frequently used toautomatically increase the amount of training data. However, in a low-resourcescenario, it is less effective due to unreliable annotations created usingself-labeling of unlabeled data. We propose to combine self-training with noisehandling on the self-labeled data. Directly estimating noise on the combinedclean training set and self-labeled data can lead to corruption of the cleandata and hence, performs worse. Thus, we propose the Clean and Noisy LabelNeural Network which trains on clean and noisy self-labeled data simultaneouslyby explicitly modelling clean and noisy labels separately. In our experimentson Chunking and NER, this approach performs more robustly than the baselines.Complementary to this explicit approach, noise can also be handled implicitlywith the help of an auxiliary learning task. To such a complementary approach,our method is more beneficial than other baseline methods and together providesthe best performance overall.

Handling Noisy Labels for Robustly Learning from Self-Training Data for Low-Resource Sequence Labeling