Convolution et marqueurs multidimensionnels. Description des représentations genrées dans un corpus de films français

Description

Convolutional neural networks allow new representations of texts that extend the standard statistical approaches. By combining frequency and context of words as well as allowing multidimensional treatments (graphical form, lemma and part of speech), convolution leads to the extraction of motifs, i.e. complex linguistic patterns that are likely to feed interpretation. In this paper, this architecture is tested on movie scripts in order to explore the hypothesis of a gendered differentiation of female and male dialogues.

Abstract

International audience

Additional details