Papers by Quentin Heinrich
FQuAD2.0: French Question Answering and Learning When You Don’t Know (2022.lrec-1)
Copied to clipboard
| Challenge: | Question Answering, including Reading Comprehension, has seen significant scientific breakthroughs over the past few years . but most of these breakthroughs are centered on the English language . |
| Approach: | They propose a dataset to train Question Answering models in the French language . they extend the dataset to 17,000+ unanswerable questions annotated adversarially . |
| Outcome: | The proposed dataset makes it possible to train French Question Answering models with the ability to distinguish unanswerable questions from answerable ones. |
FQuAD: French Question Answering Dataset (2020.findings-emnlp)
Copied to clipboard
| Challenge: | Recent advances in the field of language modeling have improved state-of-the-art results on many natural language processing tasks. |
| Approach: | They propose to use a French Question Answering Dataset to track progress of French Question answering models. |
| Outcome: | The proposed model achieves an F1 score of 92.2 and an exact match ratio of 82.1 on the test set. |