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

The current state-of-the-art task-oriented semantic parsing models use BERTor RoBERTa as pretrained encoders; these models have huge memory footprints.This poses a challenge to their deployment for voice assistants such as AmazonAlexa and Google Assistant on edge devices with limited memory budgets. Wepropose to learn compositional code embeddings to greatly reduce the sizes ofBERT-base and RoBERTa-base. We also apply the technique to DistilBERT,ALBERT-base, and ALBERT-large, three already compressed BERT variants whichattain similar state-of-the-art performances on semantic parsing with muchsmaller model sizes. We observe 95.15% ~ 98.46% embedding compression rates and20.47% ~ 34.22% encoder compression rates, while preserving greater than 97.5%semantic parsing performances. We provide the recipe for training and analyzethe trade-off between code embedding sizes and downstream performances.

Compressing Transformer-Based Semantic Parsing Models using Compositional Code Embeddings