Automatic Segmentation and tagging of facts in French for automated fact-checking
Edouard Ngor Sarr, Ousmane Sall, Aminata Maiga, Lamine Faty, Reine Marie Marone · 2018
In recent years, automatic natural language processing (NLP) has made considerable progress in terms of performance. Nevertheless, to undertake a linguistic analysis of the facts in French remains a real problem today. On the one hand, current taggers do not match the definition of fact in fact-checking and, on the other hand, the complexity of the French language considerably decreases their performance. In this paper, we propose a tool for the automatic segmentation and tagging of simple facts in French language speeches. It takes a speech as an input and generates the labelled facts as an output in table format.