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

Conversational agents such as Cortana, Alexa and Siri are continuouslyworking on increasing their capabilities by adding new domains. The support ofa new domain includes the design and development of a number of NLU componentsfor domain classification, intents classification and slots tagging (includingnamed entity recognition). Each component only performs well when trained on alarge amount of labeled data. Second, these components are deployed onlimited-memory devices which requires some model compression. Third, for somedomains such as the health domain, it is hard to find a single training dataset that covers all the required slot types. To overcome these mentionedproblems, we present a multi-task transformer-based neural architecture forslot tagging. We consider the training of a slot tagger using multiple datasets covering different slot types as a multi-task learning problem. Theexperimental results on the biomedical domain have shown that the proposedapproach outperforms the previous state-of-the-art systems for slot tagging onthe different benchmark biomedical datasets in terms of (time and memory)efficiency and effectiveness. The output slot tagger can be used by theconversational agent to better identify entities in the input utterances.

MT-BioNER: Multi-task Learning for Biomedical Named Entity Recognition using Deep Bidirectional Transformers