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

People often use a web search engine to find information about events ofinterest, for example, sport competitions, political elections, festivals andentertainment news. In this paper, we study a problem of detectingevent-related queries, which is the first step before selecting a suitabletime-aware retrieval model. In general, event-related information needs can beobserved in query streams through various temporal patterns of user searchbehavior, e.g., spiky peaks for popular events, and periodicities forrepetitive events. However, it is also common that users search for non-popularevents, which may not exhibit temporal variations in query streams, e.g., pastevents recently occurred, historical events triggered by anniversaries orsimilar events, and future events anticipated to happen. To address thechallenge of detecting dynamic classes of events, we propose a novel deeplearning model to classify a given query into a predetermined set of multipleevent types. Our proposed model, a Stacked Multilayer Perceptron (S-MLP)network, consists of multilayer perceptron used as a basic learning unit. Weassemble stacked units to further learn complex relationships between neutronsin successive layers. To evaluate our proposed model, we conduct experimentsusing real-world queries and a set of manually created ground truth.Preliminary results have shown that our proposed deep learning modeloutperforms the state-of-the-art classification models significantly.

Learning Dynamic Classes of Events using Stacked Multilayer Perceptron Networks