@inproceedings{L16-1585,
 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.
},
 address = {Portorož, Slovenia},
 author = {Muhammad Humayoun and Hwanjo Yu},
 booktitle = {Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC 2016)},
 month = {May},
 pages = {3686--3693},
 publisher = {European Language Resources Association (ELRA)},
 title = {Analyzing Pre-processing Settings for Urdu Single-document Extractive Summarization},
 url = {https://www.aclweb.org/anthology/L16-1585},
 year = {2016}
}