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

Capturing sentence semantics plays a vital role in a range of text miningapplications. Despite continuous efforts on the development of related datasetsand models in the general domain, both datasets and models are limited inbiomedical and clinical domains. The BioCreative/OHNLP organizers have made thefirst attempt to annotate 1,068 sentence pairs from clinical notes and havecalled for a community effort to tackle the Semantic Textual Similarity(BioCreative/OHNLP STS) challenge. We developed models using traditionalmachine learning and deep learning approaches. For the post challenge, we focuson two models: the Random Forest and the Encoder Network. We applied sentenceembeddings pre-trained on PubMed abstracts and MIMIC-III clinical notes andupdated the Random Forest and the Encoder Network accordingly. The officialresults demonstrated our best submission was the ensemble of eight models. Itachieved a Person correlation coefficient of 0.8328, the highest performanceamong 13 submissions from 4 teams. For the post challenge, the performance ofboth Random Forest and the Encoder Network was improved; in particular, thecorrelation of the Encoder Network was improved by ~13%. During the challengetask, no end-to-end deep learning models had better performance than machinelearning models that take manually-crafted features. In contrast, with thesentence embeddings pre-trained on biomedical corpora, the Encoder Network nowachieves a correlation of ~0.84, which is higher than the original best model.The ensembled model taking the improved versions of the Random Forest andEncoder Network as inputs further increased performance to 0.8528. Deeplearning models with sentence embeddings pre-trained on biomedical corporaachieve the highest performance on the test set.

Deep learning with sentence embeddings pre-trained on biomedical corpora  improves the performance of finding similar sentences in electronic medical  records