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

Expanding new functionalities efficiently is an ongoing challenge forsingle-turn task-oriented dialogue systems. In this work, we explorefunctionality-specific semi-supervised learning via self-training. We considermethods that augment training data automatically from unlabeled data sets in afunctionality-targeted manner. In addition, we examine multiple techniques forefficient selection of augmented utterances to reduce training time andincrease diversity. First, we consider paraphrase detection methods thatattempt to find utterance variants of labeled training data with good coverage.Second, we explore sub-modular optimization based on n-grams features forutterance selection. Experiments show that functionality-specific self-trainingis very effective for improving system performance. In addition, methodsoptimizing diversity can reduce training data in many cases to 50% with littleimpact on performance.

Efficient Semi-Supervised Learning for Natural Language Understanding by Optimizing Diversity