An Experimental Analysis of Feature Selection and Similarity Assessment for Textual Summarization

Ramos, Ana Maria Schwendler; Woloszyn, Vinicius; Wives, Leandro Krug

doi:10.1007/978-3-319-66562-7_11

Cited by 2 publications

(1 citation statement)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Automatic Text Summarization (ATS) techniques have been successfully employed on user-content to highlight the most relevant information among the documents [Erkan and Radev 2004, Ganesan et al 2010, Saggion and Poibeau 2013, Ramos et al 2017. Regarding the techniques employed, several works have explored unsupervised methods based on graph centrality.…”

Section: Related Workmentioning

confidence: 99%

BEATnIk: an algorithm to Automatic generation of educational description of movies

Woloszyn

Machado

Oliveira

et al. 2017

Anais Do XXVIII Simpósio Brasileiro De Informática Na Educação (SBIE 2017)

Self Cite

View full text Add to dashboard Cite

Abstract. Teachers have increasingly employed different methods to enrich the learning of a subject in class, drive other assignments, and meet curriculum standards. One of such methods is the use of movies as an alternative educational experience to support class discussions. In this sense, websites such as TeachWithMovies 1 , arise as a valuable support to the creation of lesson plans. In this website, each movie is described as a lesson plan targeting the learning of a subject. However, the creation of such lesson plan or even a simple educational description of the movie can demand much work and time, since the text describing the teaching plan must consider educational aspects of the movie. In this work, we propose BEATnIk (Biased Educational Automatic Text summarIzation), which is an unsupervised algorithm to automatically generate movies' summaries. Such algorithm favors educational aspects from the text to generate a biased educational summary. The experiments conducted show that our approach statistically outperforms a baseline in precision, recall, and f-score.

show abstract

Section: Related Workmentioning

confidence: 99%