Summary of the paper

Title Evaluation Approaches for an Arabic Extractive Generic Text Summarization System
Authors Ibrahim Sobh, Nevin Darwish and Magda Fayek
Abstract The advance of technology and extensive use of the web has prompt the need to summarization of text documents. Users tend to extract the most informative or indicative information instead of reading the whole original documents. Naturally, automatic text summarization will save time and effort for the users, and will enable them to make decisions in less time. This paper introduces evaluation methods for an Arabic extractive text summarization system. This system integrates Bayesian and Genetic Programming (GP) classification methods in an optimized way to extract the summary sentences. The system is trainable and uses manually annotated corpus. We have introduced methods for evaluating the summary against other human summaries. Moreover, we used human judgement for system output, and finally we tested the system against a commercial Arabic summarization system.
Topics Exploitation of LRs in different types of applications (information extraction, information retrieval, speech dictation, translation, summarisation, web services, semantic web, etc.)
Full paper Evaluation Approaches for an Arabic Extractive Generic Text Summarization System
Bibtex @InProceedings{SOBH09.38,
  author = {Ibrahim Sobh, Nevin Darwish and Magda Fayek},
  title = {Evaluation Approaches for an Arabic Extractive Generic Text Summarization System},
  booktitle = {Proceedings of the Second International Conference on Arabic Language Resources and Tools},
  year = {2009},
  month = {April},
  date = {22-23},
  address = {Cairo, Egypt},
  editor = {Khalid Choukri and Bente Maegaard},
  publisher = {The MEDAR Consortium},
  isbn = {2-9517408-5-9},
  language = {english}
  }

Powered by ELDA © 2009 The MEDAR Consortium