Advanced search
Start date
Betweenand

Multi-document Summarization for Portuguese: New Frontiers

Abstract

Multi-document Summarization (MDS) aims at producing a unique summary from a group of texts on the same topic. With the huge amount of available information nowadays, mainly on the web, the usefulness of this task is evident. Investigations on MDS started at the middle of the 90s for English, and only more recently, from the middle of 2000 on, that it has been the focus of systematic research for the Portuguese language. For this reason, currently, the Portuguese language counts with reference corpora for MDS, basic text processing and analysis tools, and state of the art summarization methods, which resulted in widely available resources, tools and applications to the research community. This research proposal aims at providing continuity to this research line. On the one hand, we intend to keep developing and improving computational linguistic resources and text analysis tools, which are essential for the advance in the MDS area; on the other hand, we intend to investigate new MDS frontiers, already tackled for other languages but new for Portuguese, particularly, the update and opinion summarization. In update summarization, summaries are created that report only the new/unknown information to the reader; in opinion summarization, summaries that synthesize opinionated texts about some object, as electronic products, are created, in order to support the user assessment and decisions. While, in the first research front, the update summarization is a methodological challenge that move forward what has been done in MDS for Portuguese, on the other front there is not only the research perspective, but also the application for the final user. Besides the training and qualification of human resources and the creation of a critical mass of researchers in the area, which is very small in Brazil, this project has potential to achieve significant contributions in the area by proposing innovative methods. (AU)

Articles published in Agência FAPESP Newsletter about the research grant:
More itemsLess items
Articles published in other media outlets ( ):
More itemsLess items
VEICULO: TITULO (DATA)
VEICULO: TITULO (DATA)

Scientific publications
(References retrieved automatically from Web of Science and SciELO through information on FAPESP grants and their corresponding numbers as mentioned in the publications by the authors)
NOBREGA, FERNANDO A. A.; JORGE, ALIPIO M.; BRAZDIL, PAVEL; PARDO, THIAGO A. S.; QUARESMA, P; VIEIRA, R; ALUISIO, S; MONIZ, H; BATISTA, F; GONCALVES, T. Sentence Compression for Portuguese. COMPUTATIONAL PROCESSING OF THE PORTUGUESE LANGUAGE, PROPOR 2020, v. 12037, p. 11-pg., . (15/17841-3)