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

Text classification is a very classic NLP task, but it has two prominentshortcomings: On the one hand, text classification is deeply domain-dependent.That is, a classifier trained on the corpus of one domain may not perform sowell in another domain. On the other hand, text classification models require alot of annotated data for training. However, for some domains, there may notexist enough annotated data. Therefore, it is valuable to investigate how toefficiently utilize text data from different domains to improve the performanceof models in various domains. Some multi-domain text classification models aretrained by adversarial training to extract shared features among all domainsand the specific features of each domain. We noted that the distinctness of thedomain-specific features is different, so in this paper, we propose to use acurriculum learning strategy based on keyword weight ranking to improve theperformance of multi-domain text classification models. The experimentalresults on the Amazon review and FDU-MTL datasets show that our curriculumlearning strategy effectively improves the performance of multi-domain textclassification models based on adversarial learning and outperformsstate-of-the-art methods.

A Curriculum Learning Approach for Multi-domain Text Classification Using Keyword weight Ranking