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 growing deluge of scientific publications demands text analysis toolsthat can help scientists and policy-makers navigate, forecast and beneficiallyguide scientific research. Recent advances in natural language understandingdriven by deep transformer networks offer new possibilities for mappingscience. Because the same surface text can take on multiple and sometimescontradictory specialized senses across distinct research communities,sensitivity to context is critical for infometric applications. Transformerembedding models such as BERT capture shades of association and connotationthat vary across the different linguistic contexts of any particular word orspan of text. Here we report a procedure for encoding scientific documents withthese tools, measuring their improvement over static word embeddings in anearest-neighbor retrieval task. We find discriminability of contextualrepresentations is strongly influenced by choice of pooling strategy forsummarizing the high-dimensional network activations. Importantly, we note thatfundamentals such as domain-matched training data are more important thanstate-of-the-art NLP tools. Yet state-of-the-art models did offer significantgains. The best approach we investigated combined domain-matched pretraining,sound pooling, and state-of-the-art deep transformer network encoders. Finally,with the goal of leveraging contextual representations from deep encoders, wepresent a range of measurements for understanding and forecasting researchcommunities in science.

Semantic maps and metrics for science Semantic maps and metrics for science using deep transformer encoders