FQuAD: French Question Answering Dataset

Abstract

Recent advances in the field of language modeling have improved state-of-the-art results on many Natural Language Processing tasks. Among them, the Machine Reading Comprehension task has made significant progress. However, most of the results are essentially reported in English since labeled resources available in other languages, such as French, remain scarce. In the present work, we introduce the French Question Answering Dataset (FQuAD). FQuAD is French Native Reading Comprehension dataset that consists of 25,000+ questions created by higher education students on a set of Wikipedia articles. The dataset analysis, similar to SQuAD, is presented to evaluate the nature of the annotated questions and answers. To assess the quality of the dataset, a baseline model is trained which achieves a F1 score of 88.0% and an exact match ratio of 77.9% on the test set. In addition to that, a performance analysis based on the questions type and the influence of the number of training samples are explored.

Publication
French Question Answering Dataset