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

Contextually aware intelligent agents are often required to understand theusers and their surroundings in real-time. Our goal is to build ArtificialIntelligence (AI) systems that can assist children in their learning process.Within such complex frameworks, Spoken Dialogue Systems (SDS) are crucialbuilding blocks to handle efficient task-oriented communication with childrenin game-based learning settings. We are working towards a multimodal dialoguesystem for younger kids learning basic math concepts. Our focus is on improvingthe Natural Language Understanding (NLU) module of the task-oriented SDSpipeline with limited datasets. This work explores the potential benefits ofdata augmentation with paraphrase generation for the NLU models trained onsmall task-specific datasets. We also investigate the effects of extractingentities for conceivably further data expansion. We have shown thatparaphrasing with model-in-the-loop (MITL) strategies using small seed data isa promising approach yielding improved performance results for the IntentRecognition task.

Data Augmentation with Paraphrase Generation and Entity Extraction for Multimodal Dialogue System