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 the natural language processing literature, neural networks are becomingincreasingly deeper and complex. The recent poster child of this trend is thedeep language representation model, which includes BERT, ELMo, and GPT. Thesedevelopments have led to the conviction that previous-generation, shallowerneural networks for language understanding are obsolete. In this paper,however, we demonstrate that rudimentary, lightweight neural networks can stillbe made competitive without architecture changes, external training data, oradditional input features. We propose to distill knowledge from BERT, astate-of-the-art language representation model, into a single-layer BiLSTM, aswell as its siamese counterpart for sentence-pair tasks. Across multipledatasets in paraphrasing, natural language inference, and sentimentclassification, we achieve comparable results with ELMo, while using roughly100 times fewer parameters and 15 times less inference time.

Distilling Task-Specific Knowledge from BERT into Simple Neural Networks