Supervising the Centroid Baseline for Extractive Multi-Document Summarization

Gonçalves, Simão, Correia, Gonçalo, Pernes, Diogo, Mendes, Afonso

arXiv.org Artificial Intelligence 

In this work, we refine the centroid method even further: i) we utilize multilingual sentence embeddings Multi-document summarization (MDS) addresses to enable summarization of clusters of the need to condense content from multiple source documents in various languages; ii) we employ documents into concise and coherent summaries beam search for sentence selection, leading to a while preserving the essential context and meaning.