@inproceedings{humayoun-yu-2016-analyzing,
    title = "Analyzing Pre-processing Settings for {U}rdu Single-document Extractive Summarization",
    author = "Humayoun, Muhammad  and
      Yu, Hwanjo",
    editor = "Calzolari, Nicoletta  and
      Choukri, Khalid  and
      Declerck, Thierry  and
      Goggi, Sara  and
      Grobelnik, Marko  and
      Maegaard, Bente  and
      Mariani, Joseph  and
      Mazo, Helene  and
      Moreno, Asuncion  and
      Odijk, Jan  and
      Piperidis, Stelios",
    booktitle = "Proceedings of the Tenth International Conference on Language Resources and Evaluation ({LREC}'16)",
    month = may,
    year = "2016",
    address = "Portoro{\v{z}}, Slovenia",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/ingest-emnlp/L16-1585/",
    pages = "3686--3693",
    abstract = "Preprocessing is a preliminary step in many fields including IR and NLP. The effect of basic preprocessing settings on English for text summarization is well-studied. However, there is no such effort found for the Urdu language (with the best of our knowledge). In this study, we analyze the effect of basic preprocessing settings for single-document text summarization for Urdu, on a benchmark corpus using various experiments. The analysis is performed using the state-of-the-art algorithms for extractive summarization and the effect of stopword removal, lemmatization, and stemming is analyzed. Results showed that these pre-processing settings improve the results."
}