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 with Unanswerable Questions is a difficult NLPtask, challenged by the questions which can not be answered from passages. Itis observed that subtle literal changes often make an answerable questionunanswerable, however, most MRC models fail to recognize such changes. Toaddress this problem, in this paper, we propose a span-based method ofContrastive Learning (spanCL) which explicitly contrast answerable questionswith their answerable and unanswerable counterparts at the answer span level.With spanCL, MRC models are forced to perceive crucial semantic changes fromslight literal differences. Experiments on SQuAD 2.0 dataset show that spanCLcan improve baselines significantly, yielding 0.86-2.14 absolute EMimprovements. Additional experiments also show that spanCL is an effective wayto utilize generated questions.

To Answer or Not to Answer? Improving Machine Reading Comprehension Model with Span-based Contrastive Learning