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 integration of multi-document pre-training objectives into languagemodels has resulted in remarkable improvements in multi-document downstreamtasks. In this work, we propose extending this idea by pre-training a genericmulti-document model from a novel cross-document question answeringpre-training objective. To that end, given a set (or cluster) oftopically-related documents, we systematically generate semantically-orientedquestions from a salient sentence in one document and challenge the model,during pre-training, to answer these questions while "peeking" into othertopically-related documents. In a similar manner, the model is also challengedto recover the sentence from which the question was generated, again whileleveraging cross-document information. This novel multi-document QA formulationdirects the model to better recover cross-text informational relations, andintroduces a natural augmentation that artificially increases the pre-trainingdata. Further, unlike prior multi-document models that focus on eitherclassification or summarization tasks, our pre-training objective formulationenables the model to perform tasks that involve both short text generation(e.g., QA) and long text generation (e.g., summarization). Following thisscheme, we pre-train our model -- termed QAmden -- and evaluate its performanceacross several multi-document tasks, including multi-document QA,summarization, and query-focused summarization, yielding improvements of up to7%, and significantly outperforms zero-shot GPT-3.5 and GPT-4.

Peek Across: Improving Multi-Document Modeling via Cross-Document Question-Answering