Basic Methods for Multilingual Multidocument Summarization

• Grant number: 11/07617-8
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Start date: October 01, 2011
• End date: February 29, 2012
• Field of knowledge: Linguistics, Literature and Arts - Linguistics - Linguistic Theory and Analysis
• Principal Investigator: Ariani Di Felippo
• Grantee: Fabricio Elder da Silva Tosta
• Host Institution: Centro de Educação e Ciências Humanas (CECH). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

The large amount of information available in several languages, especially on-line, has created a demand for automating the multilingual multi-document summarization (SAMM) task in the Natural Language Processing field called Automatic Summarization (AS). The aim of the SAMM is to process collections of related documents, and extract content from it, while removing redundancy and taking into account similarities and differences in information content, and present the most relevant content to the user in a condensed form. There was no information about research on SAMM involving the Brazilian Portuguese. Given this scenario, basic methods of SA, based on shallow approaches, will be investigated in SAMM. Such methods are characterized by the simplest treatment of linguistic phenomena and low cost production of summaries.