Sentence-Pair Classification

DACCORD is a new dataset dedicated to the task of automatically detecting contradictions between sentences in French. The dataset is currently composed of 1034 sentence pairs. It covers the themes of Russia’s invasion of Ukraine in 2022, the Covid-19 pandemic, and the climate crisis.

GQNLI-FR is a manually translated French version of the GQNLI challenge dataset, originally written in English. GQNLI is an evaluation corpus that is aimed for testing language model's generalized quantifier reasoning ability. The dataset can be used for the task of Natural Language Inference (NLI), also known as Recognizing Textual Entailment (RTE), which is a sentence-pair classification task.

RTE3-FR dataset is the French translation of the Textual Entailment English dataset used in the RTE-3 Challenge (https://nlp.stanford.edu/RTE3-pilot). Like its English counterpart, the French RTE-3 dataset is composed of a development set and a test set, each containing 800 T/H pairs. The dataset is annotated for a 3-way task with the following labels: entailment (0), neutral (1), contradiction (2). RTE3-FR is available both in XML and TSV format.