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

To build a French national electronic injury surveillance system based onemergency room visits, we aim to develop a coding system to classify theircauses from clinical notes in free-text. Supervised learning techniques haveshown good results in this area but require a large amount of expert annotateddataset which is time consuming and costly to obtain. We hypothesize that theNatural Language Processing Transformer model incorporating a generativeself-supervised pre-training step can significantly reduce the required numberof annotated samples for supervised fine-tuning. In this preliminary study, wetest our hypothesis in the simplified problem of predicting whether a visit isthe consequence of a traumatic event or not from free-text clinical notes.Using fully re-trained GPT-2 models (without OpenAI pre-trained weights), weassess the gain of applying a self-supervised pre-training phase with unlabelednotes prior to the supervised learning task. Results show that the number ofdata required to achieve a ginve level of performance (AUC>0.95) was reduced bya factor of 10 when applying pre-training. Namely, for 16 times more data, thefully-supervised model achieved an improvement <1% in AUC. To conclude, it ispossible to adapt a multi-purpose neural language model such as the GPT-2 tocreate a powerful tool for classification of free-text notes with only a smallnumber of labeled samples.

Pre-training A Neural Language Model Improves The Sample Efficiency of an Emergency Room Classification Model