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

Deep learning provides a promising way to extract effective representationsfrom raw data in an end-to-end fashion and has proven its effectiveness invarious domains such as computer vision, natural language processing, etc.However, in domains such as content/product recommendation and risk management,where sequence of event data is the most used raw data form and experts derivedfeatures are more commonly used, deep learning models struggle to dominate thegame. In this paper, we propose a symbolic testing framework that helps toanswer the question of what kinds of expert-derived features could be learnedby a neural network. Inspired by this testing framework, we introduce anefficient architecture named SHORING, which contains two components:\textit{event network} and \textit{sequence network}. The \textit{event}network learns arbitrarily yet efficiently high-order \textit{event-level}embeddings via a provable reparameterization trick, the \textit{sequence}network aggregates from sequence of \textit{event-level} embeddings. We arguethat SHORING is capable of learning certain standard symbolic expressions whichthe standard multi-head self-attention network fails to learn, and conductcomprehensive experiments and ablation studies on four synthetic datasets andthree real-world datasets. The results show that SHORING empiricallyoutperforms the state-of-the-art methods.

SHORING: Design Provable Conditional High-Order Interaction Network via Symbolic Testing