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

This paper introduces STRASS: Summarization by TRAnsformation Selection andScoring. It is an extractive text summarization method which leverages thesemantic information in existing sentence embedding spaces. Our method createsan extractive summary by selecting the sentences with the closest embeddings tothe document embedding. The model learns a transformation of the documentembedding to minimize the similarity between the extractive summary and theground truth summary. As the transformation is only composed of a dense layer,the training can be done on CPU, therefore, inexpensive. Moreover, inferencetime is short and linear according to the number of sentences. As a secondcontribution, we introduce the French CASS dataset, composed of judgments fromthe French Court of cassation and their corresponding summaries. On thisdataset, our results show that our method performs similarly to the state ofthe art extractive methods with effective training and inferring time.

STRASS: A Light and Effective Method for Extractive Summarization Based on Sentence Embeddings