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

Pre-trained Language Models (PLMs) have achieved remarkable performance forvarious language understanding tasks in IR systems, which require thefine-tuning process based on labeled training data. For low-resource scenarios,prompt-based learning for PLMs exploits prompts as task guidance and turnsdownstream tasks into masked language problems for effective few-shotfine-tuning. In most existing approaches, the high performance of prompt-basedlearning heavily relies on handcrafted prompts and verbalizers, which may limitthe application of such approaches in real-world scenarios. To solve thisissue, we present CP-Tuning, the first end-to-end Contrastive Prompt Tuningframework for fine-tuning PLMs without any manual engineering of task-specificprompts and verbalizers. It is integrated with the task-invariant continuousprompt encoding technique with fully trainable prompt parameters. We furtherpropose the pair-wise cost-sensitive contrastive learning procedure to optimizethe model in order to achieve verbalizer-free class mapping and enhance thetask-invariance of prompts. It explicitly learns to distinguish differentclasses and makes the decision boundary smoother by assigning different coststo easy and hard cases. Experiments over a variety of language understandingtasks used in IR systems and different PLMs show that CP-Tuning outperformsstate-of-the-art methods.

Making Pre-trained Language Models End-to-end Few-shot Learners with Contrastive Prompt Tuning