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

Continual learning refers to a dynamical framework in which a model receivesa stream of non-stationary data over time and must adapt to new data whilepreserving previously acquired knowledge. Unluckily, neural networks fail tomeet these two desiderata, incurring the so-called catastrophic forgettingphenomenon. Whereas a vast array of strategies have been proposed to attenuateforgetting in the computer vision domain, for speech-related tasks, on theother hand, there is a dearth of works. In this paper, we consider the jointuse of rehearsal and knowledge distillation (KD) approaches for spoken languageunderstanding under a class-incremental learning scenario. We report onmultiple KD combinations at different levels in the network, showing thatcombining feature-level and predictions-level KDs leads to the best results.Finally, we provide an ablation study on the effect of the size of therehearsal memory that corroborates the efficacy of our approach forlow-resource devices.

An Investigation of the Combination of Rehearsal and Knowledge Distillation in Continual Learning for Spoken Language Understanding