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

Recently, more and more people study online for the convenience of access tomassive learning materials (e.g. test questions/notes), thus accuratelyunderstanding learning materials became a crucial issue, which is essential formany educational applications. Previous studies focus on using language modelsto represent the question data. However, test questions (TQ) are usuallyheterogeneous and multi-modal, e.g., some of them may only contain text, whileothers half contain images with information beyond their literal description.In this context, both supervised and unsupervised methods are difficult tolearn a fused representation of questions. Meanwhile, this problem cannot besolved by conventional methods such as image caption, as the images may containinformation complementary rather than duplicate to the text. In this paper, wefirst improve previous text-only representation with a two-stage unsupervisedinstance level contrastive based pre-training method (MCL: Mixture UnsupervisedContrastive Learning). Then, TQ-Net was proposed to fuse the content of imagesto the representation of heterogeneous data. Finally, supervised contrastivelearning was conducted on relevance prediction-related downstream tasks, whichhelped the model to learn the representation of questions effectively. Weconducted extensive experiments on question-based tasks on large-scale,real-world datasets, which demonstrated the effectiveness of TQ-Net and improvethe precision of downstream applications (e.g. similar questions +2.02% andknowledge point prediction +7.20%). Our code will be available, and we willopen-source a subset of our data to promote the development of relativestudies.

TQ-Net: Mixed Contrastive Representation Learning For Heterogeneous Test Questions