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

We argue that disentangling content selection from the budget used to coversalient content improves the performance and applicability of abstractivesummarizers. Our method, FactorSum, does this disentanglement by factorizingsummarization into two steps through an energy function: (1) generation ofabstractive summary views; (2) combination of these views into a final summary,following a budget and content guidance. This guidance may come from differentsources, including from an advisor model such as BART or BigBird, or in oraclemode -- from the reference. This factorization achieves significantly higherROUGE scores on multiple benchmarks for long document summarization, namelyPubMed, arXiv, and GovReport. Most notably, our model is effective for domainadaptation. When trained only on PubMed samples, it achieves a 46.29 ROUGE-1score on arXiv, which indicates a strong performance due to more flexiblebudget adaptation and content selection less dependent on domain-specifictextual structure.

Factorizing Content and Budget Decisions in Abstractive Summarization of Long Documents