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

As an essential task in task-oriented dialog systems, slot filling requiresextensive training data in a certain domain. However, such data are not alwaysavailable. Hence, cross-domain slot filling has naturally arisen to cope withthis data scarcity problem. In this paper, we propose a Coarse-to-fine approach(Coach) for cross-domain slot filling. Our model first learns the generalpattern of slot entities by detecting whether the tokens are slot entities ornot. It then predicts the specific types for the slot entities. In addition, wepropose a template regularization approach to improve the adaptation robustnessby regularizing the representation of utterances based on utterance templates.Experimental results show that our model significantly outperformsstate-of-the-art approaches in slot filling. Furthermore, our model can also beapplied to the cross-domain named entity recognition task, and it achievesbetter adaptation performance than other existing baselines. The code isavailable at https://github.com/zliucr/coach.

Coach: A Coarse-to-Fine Approach for Cross-domain Slot Filling