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

In natural language processing (NLP), state-of-the-art (SOTA) semi-supervisedlearning (SSL) frameworks have shown great performance on deep pre-trainedlanguage models such as BERT, and are expected to significantly reduce thedemand for manual labeling. However, our empirical studies indicate that theseframeworks are not suitable for lightweight models such as TextCNN, LSTM andetc. In this work, we develop a new SSL framework called FLiText, which standsfor Faster and Lighter semi-supervised Text classification. FLiText introducesan inspirer network together with the consistency regularization framework,which leverages a generalized regular constraint on the lightweight models forefficient SSL. As a result, FLiText obtains new SOTA performance forlightweight models across multiple SSL benchmarks on text classification.Compared with existing SOTA SSL methods on TextCNN, FLiText improves theaccuracy of lightweight model TextCNN from 51.00% to 90.49% on IMDb, 39.8% to58.06% on Yelp-5, and from 55.3% to 65.08% on Yahoo. In addition, compared withthe fully supervised method on the full dataset, FLiText just uses less than 1%of labeled data to improve the accuracy by 6.59%, 3.94%, and 3.22% on thedatasets of IMDb, Yelp-5, and Yahoo respectively.

FLiText: A Faster and Lighter Semi-Supervised Text Classification with Convolution Networks