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

Slot filling and intent detection are two fundamental tasks in the field ofnatural language understanding. Due to the strong correlation between these twotasks, previous studies make efforts on modeling them with multi-task learningor designing feature interaction modules to improve the performance of eachtask. However, none of the existing approaches consider the relevance betweenthe structural information of sentences and the label semantics of two tasks.The intent and semantic components of a utterance are dependent on thesyntactic elements of a sentence. In this paper, we investigate a multi-grainedlabel refinement network, which utilizes dependency structures and labelsemantic embeddings. Considering to enhance syntactic representations, weintroduce the dependency structures of sentences into our model by graphattention layer. To capture the semantic dependency between the syntacticinformation and task labels, we combine the task specific features withcorresponding label embeddings by attention mechanism. The experimental resultsdemonstrate that our model achieves the competitive performance on two publicdatasets.

Multi-grained Label Refinement Network with Dependency Structures for Joint Intent Detection and Slot Filling