FreCDo: A Large Corpus for French Cross-Domain Dialect Identification

TL;DR

This paper introduces a large, bias-controlled French dialect corpus from multiple countries, enabling cross-domain dialect identification and evaluating several baseline models, including fine-tuned CamemBERT.

Contribution

The creation of a comprehensive, bias-controlled French dialect corpus for cross-domain identification and the evaluation of multiple baseline models on this dataset.

Findings

CamemBERT fine-tuning improves dialect classification accuracy.

Feature analysis reveals key discriminative cues for dialects.

Baseline models demonstrate the dataset's utility for dialect identification.

Abstract

We present a novel corpus for French dialect identification comprising 413,522 French text samples collected from public news websites in Belgium, Canada, France and Switzerland. To ensure an accurate estimation of the dialect identification performance of models, we designed the corpus to eliminate potential biases related to topic, writing style, and publication source. More precisely, the training, validation and test splits are collected from different news websites, while searching for different keywords (topics). This leads to a French cross-domain (FreCDo) dialect identification task. We conduct experiments with four competitive baselines, a fine-tuned CamemBERT model, an XGBoost based on fine-tuned CamemBERT features, a Support Vector Machines (SVM) classifier based on fine-tuned CamemBERT features, and an SVM based on word n-grams. Aside from presenting quantitative results, we also make an analysis of the most discriminative features learned by CamemBERT. Our corpus is available at https://github.com/MihaelaGaman/FreCDo.