MTEB is a benchmark that spans 8 embedding tasks covering a total of 56 datasets and 112 languages. The 8 task types are Bitext mining, Classification, Clustering, Pair Classification, Reranking, Retrieval, Semantic Textual Similarity and Summarisation. The 56 datasets contain varying text lengths and they are grouped into three categories: Sentence to sentence, Paragraph to paragraph, and Sentence to paragraph.
54 PAPERS • 8 BENCHMARKS
DACCORD is a new dataset dedicated to the task of automatically detecting contradictions between sentences in French.
1 PAPER • NO BENCHMARKS YET