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

Automated answering of natural language questions is an interesting anduseful problem to solve. Question answering (QA) systems often performinformation retrieval at an initial stage. Information retrieval (IR)performance, provided by engines such as Lucene, places a bound on overallsystem performance. For example, no answer bearing documents are retrieved atlow ranks for almost 40% of questions.  In this paper, answer texts from previous QA evaluations held as part of theText REtrieval Conferences (TREC) are paired with queries and analysed in anattempt to identify performance-enhancing words. These words are then used toevaluate the performance of a query expansion method.  Data driven extension words were found to help in over 70% of difficultquestions. These words can be used to improve and evaluate query expansionmethods. Simple blind relevance feedback (RF) was correctly predicted asunlikely to help overall performance, and an possible explanation is providedfor its low value in IR for QA.

A Data Driven Approach to Query Expansion in Question Answering