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

Machine reading comprehension has made great progress in recent years owingto large-scale annotated datasets. In the clinical domain, however, creatingsuch datasets is quite difficult due to the domain expertise required forannotation. Recently, Pampari et al. (EMNLP'18) tackled this issue by usingexpert-annotated question templates and existing i2b2 annotations to createemrQA, the first large-scale dataset for question answering (QA) based onclinical notes. In this paper, we provide an in-depth analysis of this datasetand the clinical reading comprehension (CliniRC) task. From our qualitativeanalysis, we find that (i) emrQA answers are often incomplete, and (ii) emrQAquestions are often answerable without using domain knowledge. From ourquantitative experiments, surprising results include that (iii) using a smallsampled subset (5%-20%), we can obtain roughly equal performance compared tothe model trained on the entire dataset, (iv) this performance is close tohuman expert's performance, and (v) BERT models do not beat the best performingbase model. Following our analysis of the emrQA, we further explore two desiredaspects of CliniRC systems: the ability to utilize clinical domain knowledgeand to generalize to unseen questions and contexts. We argue that both shouldbe considered when creating future datasets.

Clinical Reading Comprehension: A Thorough Analysis of the emrQA Dataset