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

The realm of scientific text summarization has experienced remarkableprogress due to the availability of annotated brief summaries and ample data.However, the utilization of multiple input modalities, such as videos andaudio, has yet to be thoroughly explored. At present, scientificmultimodal-input-based text summarization systems tend to employ longer targetsummaries like abstracts, leading to an underwhelming performance in the taskof text summarization.  In this paper, we deal with a novel task of extreme abstractive textsummarization (aka TL;DR generation) by leveraging multiple input modalities.To this end, we introduce mTLDR, a first-of-its-kind dataset for theaforementioned task, comprising videos, audio, and text, along with bothauthor-composed summaries and expert-annotated summaries. The mTLDR datasetaccompanies a total of 4,182 instances collected from various academicconference proceedings, such as ICLR, ACL, and CVPR. Subsequently, we presentmTLDRgen, an encoder-decoder-based model that employs a novel dual-fusedhyper-complex Transformer combined with a Wasserstein Riemannian EncoderTransformer, to dexterously capture the intricacies between differentmodalities in a hyper-complex latent geometric space. The hyper-complexTransformer captures the intrinsic properties between the modalities, while theWasserstein Riemannian Encoder Transformer captures the latent structure of themodalities in the latent space geometry, thereby enabling the model to producediverse sentences. mTLDRgen outperforms 20 baselines on mTLDR as well asanother non-scientific dataset (How2) across three Rouge-based evaluationmeasures. Furthermore, based on the qualitative metrics, BERTScore and FEQA,and human evaluations, we demonstrate that the summaries generated by mTLDRgenare fluent and congruent to the original source material.

Fusing Multimodal Signals on Hyper-complex Space for Extreme Abstractive Text Summarization (TL;DR) of Scientific Contents