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

Biomedical text tagging systems are plagued by the dearth of labeled trainingdata. There have been recent attempts at using pre-trained encoders to dealwith this issue. Pre-trained encoder provides representation of the input textwhich is then fed to task-specific layers for classification. The entirenetwork is fine-tuned on the labeled data from the target task. Unfortunately,a low-resource biomedical task often has too few labeled instances forsatisfactory fine-tuning. Also, if the label space is large, it contains few orno labeled instances for majority of the labels. Most biomedical taggingsystems treat labels as indexes, ignoring the fact that these labels are oftenconcepts expressed in natural language e.g. `Appearance of lesion on brainimaging'. To address these issues, we propose constructing extra labeledinstances using label-text (i.e. label's name) as input for the correspondinglabel-index (i.e. label's index). In fact, we propose a number of strategiesfor manufacturing multiple artificial labeled instances from a single label.The network is then fine-tuned on a combination of real and these newlyconstructed artificial labeled instances. We evaluate the proposed approach onan important low-resource biomedical task called \textit{PICO annotation},which requires tagging raw text describing clinical trials with labelscorresponding to different aspects of the trial i.e. PICO (Population,Intervention/Control, Outcome) characteristics of the trial. Our empiricalresults show that the proposed method achieves a new state-of-the-artperformance for PICO annotation with very significant improvements overcompetitive baselines.

Constructing Artificial Data for Fine-tuning for Low-Resource Biomedical Text Tagging with Applications in PICO Annotation