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 Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

In this paper, we study bidirectional LSTM network for the task of textclassification using both supervised and semi-supervised approaches. Severalprior works have suggested that either complex pretraining schemes usingunsupervised methods such as language modeling (Dai and Le 2015; Miyato, Dai,and Goodfellow 2016) or complicated models (Johnson and Zhang 2017) arenecessary to achieve a high classification accuracy. However, we develop atraining strategy that allows even a simple BiLSTM model, when trained withcross-entropy loss, to achieve competitive results compared with more complexapproaches. Furthermore, in addition to cross-entropy loss, by using acombination of entropy minimization, adversarial, and virtual adversariallosses for both labeled and unlabeled data, we report state-of-the-art resultsfor text classification task on several benchmark datasets. In particular, onthe ACL-IMDB sentiment analysis and AG-News topic classification datasets, ourmethod outperforms current approaches by a substantial margin. We also show thegenerality of the mixed objective function by improving the performance onrelation extraction task.

Revisiting LSTM Networks for Semi-Supervised Text Classification via Mixed Objective Function