@inproceedings{rohanian-2017-multi,
    title = "Multi-Document Summarization of {P}ersian Text using Paragraph Vectors",
    author = "Rohanian, Morteza",
    editor = "Kovatchev, Venelin  and
      Temnikova, Irina  and
      Gencheva, Pepa  and
      Kiprov, Yasen  and
      Nikolova, Ivelina",
    booktitle = "Proceedings of the Student Research Workshop Associated with {RANLP} 2017",
    month = sep,
    year = "2017",
    address = "Varna",
    publisher = "INCOMA Ltd.",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/R17-2005/",
    doi = "10.26615/issn.1314-9156.2017_005",
    pages = "35--40",
    abstract = "A multi-document summarizer finds the key topics from multiple textual sources and organizes information around them. In this paper we propose a summarization method for Persian text using paragraph vectors that can represent textual units of arbitrary lengths. We use these vectors to calculate the semantic relatedness between documents, cluster them to a number of predetermined groups, weight them based on their distance to the centroids and the intra-cluster homogeneity and take out the key paragraphs. We compare the final summaries with the gold-standard summaries of 21 digital topics using the ROUGE evaluation metric. Experimental results show the advantages of using paragraph vectors over earlier attempts at developing similar methods for a low resource language like Persian."
}