In this article we address the usefulness of linguistic-independent methods in extractive Automatic Summarization, arguing that linguistic knowledge is not only useful, but may be necessary to improve the informativeness of automatic extracts. An assessment of four diverse AS methods on Brazilian Portuguese texts is presented to support our claim. One of them is Mihalcea’s TextRank; other two are modified versions of the former through the inclusion of varied linguistic features. Finally, the fourth method employs machine learning techniques, tackling more profound and language-dependent knowledge.
|Publisher||Association for Computational Linguistics|
|Conference||Proceedings of ACL-PASCAL Workshop on Textual Entailment and Paraphrasing, Prague, Czech Republic|
|City||East Stroudsburg, PA, USA|
|Period||1/06/07 → …|