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

Current text classification methods typically require a good number ofhuman-labeled documents as training data, which can be costly and difficult toobtain in real applications. Humans can perform classification without seeingany labeled examples but only based on a small set of words describing thecategories to be classified. In this paper, we explore the potential of onlyusing the label name of each class to train classification models on unlabeleddata, without using any labeled documents. We use pre-trained neural languagemodels both as general linguistic knowledge sources for category understandingand as representation learning models for document classification. Our method(1) associates semantically related words with the label names, (2) findscategory-indicative words and trains the model to predict their impliedcategories, and (3) generalizes the model via self-training. We show that ourmodel achieves around 90% accuracy on four benchmark datasets including topicand sentiment classification without using any labeled documents but learningfrom unlabeled data supervised by at most 3 words (1 in most cases) per classas the label name.

Text Classification Using Label Names Only: A Language Model Self-Training Approach