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

While deep learning is a powerful tool for natural language processing (NLP)problems, successful solutions to these problems rely heavily on large amountsof annotated samples. However, manually annotating data is expensive andtime-consuming. Active Learning (AL) strategies reduce the need for hugevolumes of labeled data by iteratively selecting a small number of examples formanual annotation based on their estimated utility in training the given model.In this paper, we argue that since AL strategies choose examples independently,they may potentially select similar examples, all of which may not contributesignificantly to the learning process. Our proposed approach,Active$\mathbf{^2}$ Learning (A$\mathbf{^2}$L), actively adapts to the deeplearning model being trained to eliminate such redundant examples chosen by anAL strategy. We show that A$\mathbf{^2}$L is widely applicable by using it inconjunction with several different AL strategies and NLP tasks. We empiricallydemonstrate that the proposed approach is further able to reduce the datarequirements of state-of-the-art AL strategies by $\approx \mathbf{3-25\%}$ onan absolute scale on multiple NLP tasks while achieving the same performancewith virtually no additional computation overhead.

Active$^2$ Learning: Actively reducing redundancies in Active Learning methods for Sequence Tagging and Machine Translation