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

To accomplish the punctuation restoration task, most existing approachesfocused on leveraging extra information (e.g., part-of-speech tags) oraddressing the class imbalance problem. Recent works have widely applied thetransformer-based language models and significantly improved theireffectiveness. To the best of our knowledge, an inherent issue has remainedneglected: the attention of individual heads in the transformer will be dilutedor powerless while feeding the long non-punctuation utterances. Since thoseprevious contexts, not the followings, are comparatively more valuable to thecurrent position, it's hard to achieve a good balance by independent attention.In this paper, we propose a novel Feature Fusion framework based on two-typeAttentions (FFA) to alleviate the shortage. It introduces a two-streamarchitecture. One module involves interaction between attention heads toencourage the communication, and another masked attention module captures thedependent feature representation. Then, it aggregates two feature embeddings tofuse information and enhances context-awareness. The experiments on the popularbenchmark dataset IWSLT demonstrate that our approach is effective. Withoutadditional data, it obtains comparable performance to the currentstate-of-the-art models.

A Context-Aware Feature Fusion Framework for Punctuation Restoration