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

The primary goal of ad-hoc retrieval (document retrieval in the context ofquestion answering) is to find relevant documents satisfied the informationneed posted in a natural language query. It requires a good understanding ofthe query and all the documents in a corpus, which is difficult because themeaning of natural language texts depends on the context, syntax,and semantics.Recently deep neural networks have been used to rank search results in responseto a query. In this paper, we devise a multi-resolution neural network(MRNN) toleverage the whole hierarchy of representations for document retrieval. Theproposed MRNN model is capable of deriving a representation that integratesrepresentations of different levels of abstraction from all the layers of thelearned hierarchical representation.Moreover, a duplex attention component isdesigned to refinethe multi-resolution representation so that an optimalcontextfor matching the query and document can be determined. Morespecifically, the first attention mechanism determines optimal context from thelearned multi-resolution representation for the query and document. The latterattention mechanism aims to fine-tune the representation so that the query andthe relevant document are closer in proximity. The empirical study shows thatMRNN with the duplex attention is significantly superior to existing modelsused for ad-hoc retrieval on benchmark datasets including SQuAD, WikiQA,QUASAR, and TrecQA.

MRNN: A Multi-Resolution Neural Network with Duplex Attention for Document Retrieval in the Context of Question Answering