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

One essential task in information extraction from the medical corpus is drugname recognition. Compared with text sources come from other domains, themedical text is special and has unique characteristics. In addition, themedical text mining poses more challenges, e.g., more unstructured text, thefast growing of new terms addition, a wide range of name variation for the samedrug. The mining is even more challenging due to the lack of labeled datasetsources and external knowledge, as well as multiple token representations for asingle drug name that is more common in the real application setting. Althoughmany approaches have been proposed to overwhelm the task, some problemsremained with poor F-score performance (less than 0.75). This paper presents anew treatment in data representation techniques to overcome some of thosechallenges. We propose three data representation techniques based on thecharacteristics of word distribution and word similarities as a result of wordembedding training. The first technique is evaluated with the standard NNmodel, i.e., MLP (Multi-Layer Perceptrons). The second technique involves twodeep network classifiers, i.e., DBN (Deep Belief Networks), and SAE (StackedDenoising Encoders). The third technique represents the sentence as a sequencethat is evaluated with a recurrent NN model, i.e., LSTM (Long Short TermMemory). In extracting the drug name entities, the third technique gives thebest F-score performance compared to the state of the art, with its averageF-score being 0.8645.

A New Data Representation Based on Training Data Characteristics to Extract Drug Named-Entity in Medical Text