WEKA-Based: Key Features and Classifier for French of Five Countries
This work addresses dialect recognition for French speakers, but it is incremental as it applies existing methods to new data.
The paper tackled the problem of distinguishing between regional French dialects from five countries using a corpus on everyday life themes, achieving experimental results through WEKA classifiers.
This paper describes a French dialect recognition system that will appropriately distinguish between different regional French dialects. A corpus of five regions - Monaco, French-speaking, Belgium, French-speaking Switzerland, French-speaking Canada and France, which is targeted forconstruction by the Sketch Engine. The content of the corpus is related to the four themes of eating, drinking, sleeping and living, which are closely linked to popular life. The experimental results were obtained through the processing of a python coded pre-processor and Waikato Environment for Knowledge Analysis (WEKA) data analytic tool which contains many filters and classifiers for machine learning.