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

Fine-tuned Bidirectional Encoder Representations from Transformers(BERT)-based sequence classification models have proven to be effective fordetecting Alzheimer's Disease (AD) from transcripts of human speech. However,previous research shows it is possible to improve BERT's performance on varioustasks by augmenting the model with additional information. In this work, we useprobing tasks as introspection techniques to identify linguistic informationnot well-represented in various layers of BERT, but important for the ADdetection task. We supplement these linguistic features in whichrepresentations from BERT are found to be insufficient with hand-craftedfeatures externally, and show that jointly fine-tuning BERT in combination withthese features improves the performance of AD classification by upto 5\% overfine-tuned BERT alone.

Augmenting BERT Carefully with Underrepresented Linguistic Features