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/

Zendy Plus

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

Zendy Tools

Zendy Open

In essence, embedding algorithms work by optimizing the distance between aword and its usual context in order to generate an embedding space that encodesthe distributional representation of words. In addition to single words or wordpieces, other features which result from the linguistic analysis of text,including lexical, grammatical and semantic information, can be used to improvethe quality of embedding spaces. However, until now we did not have a preciseunderstanding of the impact that such individual annotations and their possiblecombinations may have in the quality of the embeddings. In this paper, weconduct a comprehensive study on the use of explicit linguistic annotations togenerate embeddings from a scientific corpus and quantify their impact in theresulting representations. Our results show how the effect of such annotationsin the embeddings varies depending on the evaluation task. In general, weobserve that learning embeddings using linguistic annotations contributes toachieve better evaluation results.

On the Impact of Knowledge-based Linguistic Annotations in the Quality of Scientific Embeddings