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

Ambiguous user queries in search engines result in the retrieval of documentsthat often span multiple topics. One potential solution is for the searchengine to generate multiple refined queries, each of which relates to a subsetof the documents spanning the same topic. A preliminary step towards this goalis to generate a question that captures common concepts of multiple documents.We propose a new task of generating common question from multiple documents andpresent simple variant of an existing multi-source encoder-decoder framework,called the Multi-Source Question Generator (MSQG). We first train an RNN-basedsingle encoder-decoder generator from (single document, question) pairs. Attest time, given multiple documents, the 'Distribute' step of our MSQG modelpredicts target word distributions for each document using the trained model.The 'Aggregate' step aggregates these distributions to generate a commonquestion. This simple yet effective strategy significantly outperforms severalexisting baseline models applied to the new task when evaluated using automatedmetrics and human judgments on the MS-MARCO-QA dataset.

Generating a Common Question from Multiple Documents using Multi-source Encoder-Decoder Models