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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Question answering over RDF data like knowledge graphs has been greatlyadvanced, with a number of good systems providing crisp answers for naturallanguage questions or telegraphic queries. Some of these systems incorporatetextual sources as additional evidence for the answering process, but cannotcompute answers that are present in text alone. Conversely, the IR and NLPcommunities have addressed QA over text, but such systems barely utilizesemantic data and knowledge. This paper presents a method for complex questionsthat can seamlessly operate over a mixture of RDF datasets and text corpora, orindividual sources, in a unified framework. Our method, called UNIQORN, buildsa context graph on-the-fly, by retrieving question-relevant evidences from theRDF data and/or a text corpus, using fine-tuned BERT models. The resultinggraph typically contains all question-relevant evidences but also a lot ofnoise. UNIQORN copes with this input by a graph algorithm for Group SteinerTrees, that identifies the best answer candidates in the context graph.Experimental results on several benchmarks of complex questions with multipleentities and relations, show that UNIQORN significantly outperformsstate-of-the-art methods for heterogeneous QA -- in a full training mode, aswell as in zero-shot settings. The graph-based methodology providesuser-interpretable evidence for the complete answering process.

UNIQORN: Unified Question Answering over RDF Knowledge Graphs and Natural Language Text