Linguistic description of complementarity for Multi-document Summarization

• Grant number: 13/21135-1
• Support Opportunities: Scholarships in Brazil - Master
• Start date: March 01, 2014
• End date: February 28, 2015
• Field of knowledge: Linguistics, Literature and Arts - Linguistics - Linguistic Theory and Analysis
• Principal Investigator: Ariani Di Felippo
• Grantee: Jackson Wilke da Cruz Souza
• Host Institution: Centro de Educação e Ciências Humanas (CECH). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

Given the incredible and growing amount of available information, mainly on-line, and the difficulties and lack of time to deal with all this content, text processing applications have become increasingly relevant. Being relatively new (with origins in the mid-1990), Multi-document Summarization (MDS) is one of these applications. It aims at automatically producing a unique summary with cohesion and coherence from a group of texts on the same topic or subject. In order to produce a summary, MDS has to select the main information of the collection that generic or particular users might find important to include in a summary. To select the main information, it is important to identity the redundancy, complementarity and contradiction among the source texts. Since the complementarity has not been systematically investigated, this project aims at characterizing such linguistic phenomenon based on corpus description and identifying methods that can support the SAM process of journalistic texts in Portuguese language. This research will be based on corpus analysis.