Наборы данных MDS
material
ID: mdsdatasets
Related Papers
How “Multi” is Multi-Document Summarization?
AbstractThe task of multi-document summarization (MDS) aims at models that, given multiple documents as input, are able to generate a summary that combines disperse information, originally spread __across__ these documents. …...
UPER: Boosting Multi-Document Summarization with an Unsupervised Prompt-based Extractor
AbstractMulti-Document Summarization (MDS) commonly employs the 2-stage extract-then-abstract paradigm, which first extracts a relatively short meta-document, then feeds it into the deep neural networks to generate an abstract. Previous work …...