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

Question answering is one of the most important and difficult applications atthe border of information retrieval and natural language processing, especiallywhen we talk about complex science questions which require some form ofinference to determine the correct answer. In this paper, we present a two-stepmethod that combines information retrieval techniques optimized for questionanswering with deep learning models for natural language inference in order totackle the multi-choice question answering in the science domain. For eachquestion-answer pair, we use standard retrieval-based models to find relevantcandidate contexts and decompose the main problem into two differentsub-problems. First, assign correctness scores for each candidate answer basedon the context using retrieval models from Lucene. Second, we use deep learningarchitectures to compute if a candidate answer can be inferred from somewell-chosen context consisting of sentences retrieved from the knowledge base.In the end, all these solvers are combined using a simple neural network topredict the correct answer. This proposed two-step model outperforms the bestretrieval-based solver by over 3% in absolute accuracy.

Improving Retrieval-Based Question Answering with Deep Inference Models