MTEB文本向量化评估基准：Massive Text Embedding Benchmark

Massive Text Embedding Benchmark 文本向量化评估基准

• Bitext mining is the task of finding parallel sentences in two languages.
  双语文本挖掘是识别两种语言中语义等价句子对的任务。

• Classification is the task of assigning a label to a text.
  文本分类是为文本分配标签的任务。

• Clustering is the task of grouping similar documents together.
  文本聚类是将相似的文档分组在一起的任务。

• Pair classification is the task of determining whether two texts are similar.
  句子对分类是确定两个文本是否相似的任务。

• Reranking is the task of reordering a list of documents to improve relevance.
  重新排序是重新排序文档列表以提高相关性的任务。

• Retrieval is the task of finding relevant documents for a query.
  检索是查找与 query 相关的文档的任务。<