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 Tools annual

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 Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

End-to-end neural networks have achieved promising performances in naturallanguage generation (NLG). However, they are treated as black boxes and lackinterpretability. To address this problem, we propose a novel framework,heterogeneous rendering machines (HRM), that interprets how neural generatorsrender an input dialogue act (DA) into an utterance. HRM consists of a rendererset and a mode switcher. The renderer set contains multiple decoders that varyin both structure and functionality. For every generation step, the modeswitcher selects an appropriate decoder from the renderer set to generate anitem (a word or a phrase). To verify the effectiveness of our method, we haveconducted extensive experiments on 5 benchmark datasets. In terms of automaticmetrics (e.g., BLEU), our model is competitive with the currentstate-of-the-art method. The qualitative analysis shows that our model caninterpret the rendering process of neural generators well. Human evaluationalso confirms the interpretability of our proposed approach.

Interpretable NLG for Task-oriented Dialogue Systems with Heterogeneous Rendering Machines